Examenos

OneJev vendor · Public index

OneJev launch figure, released 1.6 checkpoint.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published. Vendor measurements only; explicit source label retained in every view.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · Public Knowledge

OneJev launch figure, released 1.6 checkpoint.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · Public Language

OneJev launch figure, released 1.6 checkpoint.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · Public Retrieval

OneJev launch figure, released 1.6 checkpoint.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · Public Tools

OneJev launch figure, released 1.6 checkpoint.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · Public Arts

OneJev launch figure, released 1.6 checkpoint.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Vendor-run Decision Index 0.3 public kit; 37 benchmarks / 140,178 requests as reported. Source quotes peers from the 16 October board. Not AA, evaluator-private Full, or S1MB. Exact execution dates, budgets and individual run variances are not published.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · OneJev held-out test set

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · GUI-agent subset

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · Image subset

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · Long-video subset

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · Short-video subset

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · Text subset

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · DecisionBench medium

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · DecisionBench hard

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · TypeSafe

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · MMBench

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev vendor · MMStar

Released OneJev 1.6 4B; vendor comparison figure.

Accuracy as printed. OneJev test set and five subsets are vendor-held-out data; denominators and detailed judge/protocol are not published. DecisionBench is not DecideBench v1.1. Bare TypeSafe/MMBench labels retain this vendor scope rather than assuming a standard revision.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: OneJev 1.6 launch · 2026-10-17 · Published aggregate observations; result reuse terms not separately specified

OneJev H200 screenshot · One question

Vendor H200 path; One question.

One H200 and one 1280×720 screenshot. Vendor-published timing, not hosted API latency; detailed hardware/runtime precision and distribution statistic unpublished.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: 2c32b28dbd8867471c7b62191bf8c7f1e6803a86 · Published aggregate observations; result reuse terms not separately specified

OneJev H200 screenshot · Ten questions in one request

Vendor H200 path; Ten questions in one request.

One H200 and one 1280×720 screenshot. Vendor-published timing, not hosted API latency; detailed hardware/runtime precision and distribution statistic unpublished.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: 2c32b28dbd8867471c7b62191bf8c7f1e6803a86 · Published aggregate observations; result reuse terms not separately specified

OneJev H200 screenshot · Per question in ten-question request

Vendor H200 path; Per question in ten-question request.

One H200 and one 1280×720 screenshot. Vendor-published timing, not hosted API latency; detailed hardware/runtime precision and distribution statistic unpublished.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17 · Revision: 2c32b28dbd8867471c7b62191bf8c7f1e6803a86 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/aegis2 / test · binary_brier. Population 100 cases / 148 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.16562494255927027,"accuracy":0.7432432432432432,"positive_recall":0.5774647887323944,"specificity":0.8961038961038961,"precision":0.8367346938775511,"balanced_accuracy":0.7367843424181453,"f1":0.6833333333333333,"true_positive":41,"false_positive":8,"false_negative":30,"true_negative":69,"positive_prevalence":0.4797297297297297,"majority_accuracy_baseline":0.5202702702702703,"constant_brier_baseline":0.24958911614317017,"brier_skill":0.3364095954237687,"baseline_adjusted_skill":0.47356868483629055,"baseline_adjusted_score":0.47356868483629055}. Counts: {"cases": 100, "expected": 148, "succeeded": 148, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/aqua_rat / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.52,"uniform_accuracy_baseline":0.2005,"fixed_answer_accuracy_baseline":0.29,"baseline_adjusted_skill":0.32394366197183105,"baseline_adjusted_score":0.32394366197183105}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/arc / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.95,"uniform_accuracy_baseline":0.2533333333333333,"fixed_answer_accuracy_baseline":0.32,"baseline_adjusted_skill":0.926470588235294,"baseline_adjusted_score":0.926470588235294}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/arct / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.82,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.53,"baseline_adjusted_skill":0.6170212765957446,"baseline_adjusted_score":0.6170212765957446}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/argument_quality / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.91,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.51,"baseline_adjusted_skill":0.8163265306122449,"baseline_adjusted_score":0.8163265306122449}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/argument_quality / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.1521817346120993,"accuracy":0.52154121522,"positive_recall":0.48501804539545557,"specificity":0.5801388718928919,"precision":0.6495382024782609,"balanced_accuracy":0.5325784586441737,"f1":0.5553497236758411,"true_positive":29.878757314,"false_positive":16.121242686,"false_negative":31.724635792,"true_negative":22.275364208,"positive_prevalence":0.61603393106,"majority_accuracy_baseline":0.61603393106,"constant_brier_baseline":0.07908707655202402,"brier_skill":-0.9242301175716505,"baseline_adjusted_skill":0.0651569172883475,"baseline_adjusted_score":0.0651569172883475}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/babi_nli / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.13896493381615,"accuracy":0.8,"positive_recall":0.76,"specificity":0.84,"precision":0.8260869565217391,"balanced_accuracy":0.8,"f1":0.7916666666666666,"true_positive":38,"false_positive":8,"false_negative":12,"true_negative":42,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.4441402647354,"baseline_adjusted_skill":0.6000000000000001,"baseline_adjusted_score":0.6000000000000001}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/banking77 / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.86,"uniform_accuracy_baseline":0.012987012987012986,"fixed_answer_accuracy_baseline":0.05,"baseline_adjusted_skill":0.8526315789473684,"baseline_adjusted_score":0.8526315789473684}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/bbq / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.94,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.4,"baseline_adjusted_skill":0.8999999999999999,"baseline_adjusted_score":0.8999999999999999}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/boardgameqa / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.53,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.36,"baseline_adjusted_skill":0.26562500000000006,"baseline_adjusted_score":0.26562500000000006}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/canttalk / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.11638399882249001,"accuracy":0.83,"positive_recall":0.98,"specificity":0.68,"precision":0.7538461538461538,"balanced_accuracy":0.8300000000000001,"f1":0.8521739130434782,"true_positive":49,"false_positive":16,"false_negative":1,"true_negative":34,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.53446400471004,"baseline_adjusted_skill":0.6600000000000001,"baseline_adjusted_score":0.6600000000000001}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/civil_comments / test · binary_brier. Population 100 cases / 700 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.08949102118648977,"accuracy":0.6762339593476749,"positive_recall":0.57725950271728,"specificity":0.7223200998974028,"precision":0.49186905718076673,"balanced_accuracy":0.6497898013073413,"f1":0.5311542465524693,"true_positive":128.37782392418012,"false_positive":132.62217607581988,"false_negative":94.0140523808077,"true_negative":344.9859476191923,"positive_prevalence":0.3177026804356969,"majority_accuracy_baseline":0.6822973195643032,"constant_brier_baseline":0.08872692397768642,"brier_skill":-0.008611785178031406,"baseline_adjusted_skill":0.29957960261468264,"baseline_adjusted_score":0.29957960261468264}. Counts: {"cases": 100, "expected": 700, "succeeded": 700, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/cladder / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.07382710623215,"accuracy":0.87,"positive_recall":0.86,"specificity":0.88,"precision":0.8775510204081632,"balanced_accuracy":0.87,"f1":0.8686868686868687,"true_positive":43,"false_positive":6,"false_negative":7,"true_negative":44,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.7046915750714,"baseline_adjusted_skill":0.74,"baseline_adjusted_score":0.74}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/clinc / test · target_mass_at_prediction. Population 151 cases / 151 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.9470198675496688,"uniform_accuracy_baseline":0.006622516556291391,"fixed_answer_accuracy_baseline":0.039735099337748346,"baseline_adjusted_skill":0.9448275862068966,"baseline_adjusted_score":0.9448275862068966}. Counts: {"cases": 151, "expected": 151, "succeeded": 151, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 151

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/commonsensemoralja-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.12077140623358332,"accuracy":0.8233333333333334,"positive_recall":0.6666666666666666,"specificity":0.98,"precision":0.970873786407767,"balanced_accuracy":0.8233333333333333,"f1":0.7905138339920948,"true_positive":100,"false_positive":3,"false_negative":50,"true_negative":147,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.5169143750656667,"baseline_adjusted_skill":0.6466666666666665,"baseline_adjusted_score":0.6466666666666665}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/contract_nli / test · target_mass_at_prediction. Population 100 cases / 1700 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.8788235294117647,"uniform_accuracy_baseline":0.3333333333333333,"fixed_answer_accuracy_baseline":0.4576470588235294,"baseline_adjusted_skill":0.7765726681127982,"baseline_adjusted_score":0.7765726681127982}. Counts: {"cases": 100, "expected": 1700, "succeeded": 1700, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/corr2cause / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.44,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.4,"baseline_adjusted_skill":0.06666666666666664,"baseline_adjusted_score":0.06666666666666664}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/creak / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.12667361184505,"accuracy":0.82,"positive_recall":0.96,"specificity":0.68,"precision":0.75,"balanced_accuracy":0.8200000000000001,"f1":0.8421052631578947,"true_positive":48,"false_positive":16,"false_negative":2,"true_negative":34,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.4933055526198,"baseline_adjusted_skill":0.6400000000000001,"baseline_adjusted_score":0.6400000000000001}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/crows_pairs / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.72,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.52,"baseline_adjusted_skill":0.4166666666666666,"baseline_adjusted_score":0.4166666666666666}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/cvbench-depth-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.9066666666666666,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.5,"baseline_adjusted_skill":0.8133333333333332,"baseline_adjusted_score":0.8133333333333332}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/cvbench-distance-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.7066666666666667,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.52,"baseline_adjusted_skill":0.38888888888888884,"baseline_adjusted_score":0.38888888888888884}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/cvbench-relation-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.8266666666666667,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.5266666666666666,"baseline_adjusted_skill":0.6338028169014085,"baseline_adjusted_score":0.6338028169014085}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/dbpedia / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.97,"uniform_accuracy_baseline":0.07142857142857142,"fixed_answer_accuracy_baseline":0.11,"baseline_adjusted_skill":0.9662921348314606,"baseline_adjusted_score":0.9662921348314606}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/defeasible_nli / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.78,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.54,"baseline_adjusted_skill":0.5217391304347826,"baseline_adjusted_score":0.5217391304347826}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/esci / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.42,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.27,"baseline_adjusted_skill":0.20547945205479448,"baseline_adjusted_score":0.20547945205479448}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/ethics / test · target_mass_at_prediction. Population 18 cases / 18 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.7222222222222222,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.6666666666666666,"baseline_adjusted_skill":0.1666666666666667,"baseline_adjusted_score":0.1666666666666667}. Counts: {"cases": 18, "expected": 18, "succeeded": 18, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 18

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/ethics / test · binary_brier. Population 82 cases / 82 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.19148598593178048,"accuracy":0.7439024390243902,"positive_recall":0.725,"specificity":0.7619047619047619,"precision":0.7435897435897436,"balanced_accuracy":0.743452380952381,"f1":0.7341772151898734,"true_positive":29,"false_positive":10,"false_negative":11,"true_negative":32,"positive_prevalence":0.4878048780487805,"majority_accuracy_baseline":0.5121951219512195,"constant_brier_baseline":0.2498512790005949,"brier_skill":0.23360013725875484,"baseline_adjusted_skill":0.48690476190476195,"baseline_adjusted_score":0.48690476190476195}. Counts: {"cases": 82, "expected": 82, "succeeded": 82, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 82

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/ethos / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.13310825513466,"accuracy":0.83,"positive_recall":0.78,"specificity":0.88,"precision":0.8666666666666667,"balanced_accuracy":0.8300000000000001,"f1":0.8210526315789474,"true_positive":39,"false_positive":6,"false_negative":11,"true_negative":44,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.46756697946136005,"baseline_adjusted_skill":0.6600000000000001,"baseline_adjusted_score":0.6600000000000001}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/few_nerd / test · target_mass_at_prediction. Population 100 cases / 358 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.7569832402234636,"uniform_accuracy_baseline":0.125,"fixed_answer_accuracy_baseline":0.2206703910614525,"baseline_adjusted_skill":0.6881720430107526,"baseline_adjusted_score":0.6881720430107526}. Counts: {"cases": 100, "expected": 358, "succeeded": 358, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/fol_nli / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.48,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.39,"baseline_adjusted_skill":0.14754098360655732,"baseline_adjusted_score":0.14754098360655732}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/followir_core17 / test · binary_brier. Population 100 cases / 200 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.166850284811935,"accuracy":0.77,"positive_recall":0.38636363636363635,"specificity":0.8782051282051282,"precision":0.4722222222222222,"balanced_accuracy":0.6322843822843822,"f1":0.425,"true_positive":17,"false_positive":19,"false_negative":27,"true_negative":137,"positive_prevalence":0.22,"majority_accuracy_baseline":0.78,"constant_brier_baseline":0.1716,"brier_skill":0.027678992937441693,"baseline_adjusted_skill":0.26456876456876444,"baseline_adjusted_score":0.26456876456876444}. Counts: {"cases": 100, "expected": 200, "succeeded": 200, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/followir_news21 / test · binary_brier. Population 100 cases / 200 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.18910600982685502,"accuracy":0.7,"positive_recall":0.08,"specificity":0.9066666666666666,"precision":0.2222222222222222,"balanced_accuracy":0.4933333333333333,"f1":0.11764705882352941,"true_positive":4,"false_positive":14,"false_negative":46,"true_negative":136,"positive_prevalence":0.25,"majority_accuracy_baseline":0.75,"constant_brier_baseline":0.1875,"brier_skill":-0.00856538574322685,"baseline_adjusted_skill":-0.01333333333333342,"baseline_adjusted_score":0}. Counts: {"cases": 100, "expected": 200, "succeeded": 200, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/followir_robust04 / test · binary_brier. Population 100 cases / 200 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.038263395480825003,"accuracy":0.945,"positive_recall":0.5789473684210527,"specificity":0.9834254143646409,"precision":0.7857142857142857,"balanced_accuracy":0.7811863913928467,"f1":0.6666666666666666,"true_positive":11,"false_positive":3,"false_negative":8,"true_negative":178,"positive_prevalence":0.095,"majority_accuracy_baseline":0.905,"constant_brier_baseline":0.085975,"brier_skill":0.5549474209848793,"baseline_adjusted_skill":0.5623727827856935,"baseline_adjusted_score":0.5623727827856935}. Counts: {"cases": 100, "expected": 200, "succeeded": 200, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-japanese-diverse-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.9733333333333334,"uniform_accuracy_baseline":0.3333333333333333,"fixed_answer_accuracy_baseline":0.3333333333333333,"baseline_adjusted_skill":0.9600000000000001,"baseline_adjusted_score":0.9600000000000001}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-japanese-diverse-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.022415833035013336,"accuracy":0.9766666666666667,"positive_recall":0.9733333333333334,"specificity":0.98,"precision":0.9798657718120806,"balanced_accuracy":0.9766666666666667,"f1":0.9765886287625418,"true_positive":146,"false_positive":3,"false_negative":4,"true_negative":147,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.9103366678599467,"baseline_adjusted_skill":0.9533333333333334,"baseline_adjusted_score":0.9533333333333334}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-japanese-knowledge-hard-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.9433333333333334,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.9244444444444445,"baseline_adjusted_score":0.9244444444444445}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-japanese-knowledge-hard-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.23093172221019667,"accuracy":0.64,"positive_recall":1,"specificity":0.28,"precision":0.5813953488372093,"balanced_accuracy":0.64,"f1":0.7352941176470589,"true_positive":150,"false_positive":108,"false_negative":0,"true_negative":42,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.07627311115921331,"baseline_adjusted_skill":0.28,"baseline_adjusted_score":0.28}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-japanese-knowledge-hard-score / test · normalized_expected_score_mae. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.23872696368832033,"normalized_score_rmse":0.2926441868730853,"constant_score_baseline":0.5,"constant_mae_baseline":0.3333333333333333,"baseline_adjusted_skill":0.2838191089350389,"baseline_adjusted_score":0.2838191089350389}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-japanese-math-formal-hard-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.38333333333333336,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.1777777777777778,"baseline_adjusted_score":0.1777777777777778}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-japanese-math-formal-hard-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.25317783847163333,"accuracy":0.55,"positive_recall":0.5133333333333333,"specificity":0.5866666666666667,"precision":0.5539568345323741,"balanced_accuracy":0.55,"f1":0.532871972318339,"true_positive":77,"false_positive":62,"false_negative":73,"true_negative":88,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.012711353886533328,"baseline_adjusted_skill":0.10000000000000009,"baseline_adjusted_score":0.10000000000000009}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-japanese-math-formal-hard-score / test · normalized_expected_score_mae. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.30388252927694276,"normalized_score_rmse":0.3533538672761364,"constant_score_baseline":0.5,"constant_mae_baseline":0.3,"baseline_adjusted_skill":-0.012941764256475974,"baseline_adjusted_score":0}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-vision-easy-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.9533333333333334,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.3,"baseline_adjusted_skill":0.9333333333333333,"baseline_adjusted_score":0.9333333333333333}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-vision-easy-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.036944378829296666,"accuracy":0.9733333333333334,"positive_recall":0.9664429530201343,"specificity":0.9801324503311258,"precision":0.9795918367346939,"balanced_accuracy":0.9732877016756301,"f1":0.972972972972973,"true_positive":144,"false_positive":3,"false_negative":5,"true_negative":148,"positive_prevalence":0.49666666666666665,"majority_accuracy_baseline":0.5033333333333334,"constant_brier_baseline":0.2499888888888889,"brier_skill":0.8522159165013246,"baseline_adjusted_skill":0.9465754033512601,"baseline_adjusted_score":0.9465754033512601}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-vision-easy-score / test · normalized_expected_score_mae. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.19845515172666145,"normalized_score_rmse":0.2544006652612963,"constant_score_baseline":0.5,"constant_mae_baseline":0.36666666666666664,"baseline_adjusted_skill":0.4587586771091051,"baseline_adjusted_score":0.4587586771091051}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-vision-hard-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.61,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.2866666666666667,"baseline_adjusted_skill":0.4532710280373831,"baseline_adjusted_score":0.4532710280373831}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-vision-hard-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.19169735575271,"accuracy":0.71,"positive_recall":0.6942675159235668,"specificity":0.7272727272727273,"precision":0.7364864864864865,"balanced_accuracy":0.710770121598147,"f1":0.7147540983606557,"true_positive":109,"false_positive":39,"false_negative":48,"true_negative":104,"positive_prevalence":0.5233333333333333,"majority_accuracy_baseline":0.5233333333333333,"constant_brier_baseline":0.24945555555555557,"brier_skill":0.23153703542185655,"baseline_adjusted_skill":0.421540243196294,"baseline_adjusted_score":0.421540243196294}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/generalization-vision-hard-score / test · normalized_expected_score_mae. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.27192918836271185,"normalized_score_rmse":0.3250298621796241,"constant_score_baseline":0.5,"constant_mae_baseline":0.3016666666666667,"baseline_adjusted_skill":0.09857727614570666,"baseline_adjusted_score":0.09857727614570666}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/go_emotions / test · binary_brier. Population 100 cases / 2800 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.09452103978801127,"accuracy":0.8387678571428572,"positive_recall":0.6355520285685944,"specificity":0.8517404492176369,"precision":0.21485580147551978,"balanced_accuracy":0.7436462388931157,"f1":0.32114483346282047,"true_positive":106.78333333333333,"false_positive":390.21666666666664,"false_negative":61.233333333333334,"true_negative":2241.766666666667,"positive_prevalence":0.060005952380952375,"majority_accuracy_baseline":0.9399940476190476,"constant_brier_baseline":0.03220097218679138,"brier_skill":-1.9353473938523864,"baseline_adjusted_skill":0.4872924777862313,"baseline_adjusted_score":0.4872924777862313}. Counts: {"cases": 100, "expected": 2800, "succeeded": 2800, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/gpqa-ja-main-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.41333333333333333,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.21777777777777776,"baseline_adjusted_score":0.21777777777777776}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/gretel_pii / test · target_mass_at_prediction. Population 100 cases / 353 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.7053824362606232,"uniform_accuracy_baseline":0.027777777777777776,"fixed_answer_accuracy_baseline":0.1274787535410765,"baseline_adjusted_skill":0.6623376623376623,"baseline_adjusted_score":0.6623376623376623}. Counts: {"cases": 100, "expected": 353, "succeeded": 353, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/gsm8k / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.73,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.3,"baseline_adjusted_skill":0.6142857142857143,"baseline_adjusted_score":0.6142857142857143}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/hans / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.10678979809127,"accuracy":0.85,"positive_recall":1,"specificity":0.7,"precision":0.7692307692307693,"balanced_accuracy":0.85,"f1":0.8695652173913043,"true_positive":50,"false_positive":15,"false_negative":0,"true_negative":35,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.5728408076349201,"baseline_adjusted_skill":0.7,"baseline_adjusted_score":0.7}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/hatecheck / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.1306486309916,"accuracy":0.84,"positive_recall":0.96,"specificity":0.72,"precision":0.7741935483870968,"balanced_accuracy":0.84,"f1":0.8571428571428571,"true_positive":48,"false_positive":14,"false_negative":2,"true_negative":36,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.47740547603359995,"baseline_adjusted_skill":0.6799999999999999,"baseline_adjusted_score":0.6799999999999999}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/hh_rlhf / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.64,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.61,"baseline_adjusted_skill":0.07692307692307698,"baseline_adjusted_score":0.07692307692307698}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/hwu64 / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.85,"uniform_accuracy_baseline":0.015625,"fixed_answer_accuracy_baseline":0.06,"baseline_adjusted_skill":0.8404255319148937,"baseline_adjusted_score":0.8404255319148937}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/impli / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.10455494081281999,"accuracy":0.87,"positive_recall":0.86,"specificity":0.88,"precision":0.8775510204081632,"balanced_accuracy":0.87,"f1":0.8686868686868687,"true_positive":43,"false_positive":6,"false_negative":7,"true_negative":44,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.58178023674872,"baseline_adjusted_skill":0.74,"baseline_adjusted_score":0.74}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jamc-qa-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.39,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.18666666666666668,"baseline_adjusted_score":0.18666666666666668}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jamp-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.67,"uniform_accuracy_baseline":0.3333333333333333,"fixed_answer_accuracy_baseline":0.3333333333333333,"baseline_adjusted_skill":0.505,"baseline_adjusted_score":0.505}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/janli-choice / test · target_mass_at_prediction. Population 285 cases / 285 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.6736842105263158,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.5263157894736842,"baseline_adjusted_skill":0.3111111111111111,"baseline_adjusted_score":0.3111111111111111}. Counts: {"cases": 285, "expected": 285, "succeeded": 285, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 285

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jcola-noul / test · binary_brier. Population 299 cases / 299 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.2549367081710702,"accuracy":0.5551839464882943,"positive_recall":0.9666666666666667,"specificity":0.14093959731543623,"precision":0.5311355311355311,"balanced_accuracy":0.5538031319910515,"f1":0.6855791962174941,"true_positive":145,"false_positive":128,"false_negative":5,"true_negative":21,"positive_prevalence":0.5016722408026756,"majority_accuracy_baseline":0.5016722408026756,"constant_brier_baseline":0.24999720361069788,"brier_skill":-0.019758239248404807,"baseline_adjusted_skill":0.10760626398210293,"baseline_adjusted_score":0.10760626398210293}. Counts: {"cases": 299, "expected": 299, "succeeded": 299, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 299

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jcommonsenseqa-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.9166666666666666,"uniform_accuracy_baseline":0.2,"fixed_answer_accuracy_baseline":0.2,"baseline_adjusted_skill":0.8958333333333331,"baseline_adjusted_score":0.8958333333333331}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jculture-mcq-noul / test · binary_brier. Population 283 cases / 283 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.33687389329091166,"accuracy":0.508833922261484,"positive_recall":0.7894736842105263,"specificity":0.26,"precision":0.4861111111111111,"balanced_accuracy":0.5247368421052632,"f1":0.6017191977077364,"true_positive":105,"false_positive":111,"false_negative":28,"true_negative":39,"positive_prevalence":0.46996466431095407,"majority_accuracy_baseline":0.5300353356890459,"constant_brier_baseline":0.24909787861004634,"brier_skill":-0.3523756009912693,"baseline_adjusted_skill":0.049473684210526336,"baseline_adjusted_score":0.049473684210526336}. Counts: {"cases": 283, "expected": 283, "succeeded": 283, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 283

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jmmlu-japan-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.77,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.6933333333333334,"baseline_adjusted_score":0.6933333333333334}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jmteb-retrieval / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.9666666666666667,"uniform_accuracy_baseline":0.20616666666666666,"fixed_answer_accuracy_baseline":0.21333333333333335,"baseline_adjusted_skill":0.9576271186440678,"baseline_adjusted_score":0.9576271186440678}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jnli-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.8133333333333334,"uniform_accuracy_baseline":0.3333333333333333,"fixed_answer_accuracy_baseline":0.3333333333333333,"baseline_adjusted_skill":0.72,"baseline_adjusted_score":0.72}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jsem-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.6466666666666666,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.37333333333333335,"baseline_adjusted_skill":0.4361702127659573,"baseline_adjusted_score":0.4361702127659573}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jsick-sts-score / test · normalized_expected_score_mae. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.14219264189175249,"normalized_score_rmse":0.17385086061331398,"constant_score_baseline":0.5,"constant_mae_baseline":0.26208333333333333,"baseline_adjusted_skill":0.457452558759609,"baseline_adjusted_score":0.457452558759609}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/jsts-score / test · normalized_expected_score_mae. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.10075942962161707,"normalized_score_rmse":0.12916182968751433,"constant_score_baseline":0.52,"constant_mae_baseline":0.24733333333333335,"baseline_adjusted_skill":0.5926168613681251,"baseline_adjusted_score":0.5926168613681251}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/koniq-score / test · normalized_expected_score_mae. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.12905738848986195,"normalized_score_rmse":0.1525049113630803,"constant_score_baseline":0.578319964349225,"constant_mae_baseline":0.11212962028602311,"baseline_adjusted_skill":-0.15096607087992497,"baseline_adjusted_score":0}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/kuci-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.7133333333333334,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.6177777777777779,"baseline_adjusted_score":0.6177777777777779}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/laya__ag_news / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.86,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.33,"baseline_adjusted_skill":0.7910447761194032,"baseline_adjusted_score":0.7910447761194032}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/laya__enron_spam / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.08029378272079,"accuracy":0.89,"positive_recall":0.8,"specificity":0.98,"precision":0.975609756097561,"balanced_accuracy":0.89,"f1":0.8791208791208791,"true_positive":40,"false_positive":1,"false_negative":10,"true_negative":49,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.6788248691168399,"baseline_adjusted_skill":0.78,"baseline_adjusted_score":0.78}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/laya__typed_decisions / test · target_mass_at_prediction. Population 100 cases / 148 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.46589310135135137,"uniform_accuracy_baseline":0.23445945945945948,"fixed_answer_accuracy_baseline":0.2623439054054054,"baseline_adjusted_skill":0.2759405059315801,"baseline_adjusted_score":0.2759405059315801}. Counts: {"cases": 100, "expected": 148, "succeeded": 148, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/laya__typed_decisions / test · binary_brier. Population 100 cases / 152 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.05133506620455263,"accuracy":0.6813157434210526,"positive_recall":0.8207444771751627,"specificity":0.5485486340309004,"precision":0.6338541458333333,"balanced_accuracy":0.6846465556030316,"f1":0.715293251758083,"true_positive":60.849998,"false_positive":35.150002,"false_negative":13.290005,"true_negative":42.709995,"positive_prevalence":0.4877631776315789,"majority_accuracy_baseline":0.512236822368421,"constant_brier_baseline":0.09451910039768556,"brier_skill":0.45688156162550986,"baseline_adjusted_skill":0.3692931112060631,"baseline_adjusted_score":0.3692931112060631}. Counts: {"cases": 100, "expected": 152, "succeeded": 152, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/laya__typed_decisions / test · normalized_expected_score_mae. Population 100 cases / 200 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.1253170054535956,"normalized_score_rmse":0.17325684545171366,"constant_score_baseline":0.5841668333333333,"constant_mae_baseline":0.21700552708333334,"baseline_adjusted_skill":0.42251698775639024,"baseline_adjusted_score":0.42251698775639024}. Counts: {"cases": 100, "expected": 200, "succeeded": 200, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/lexcomp / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.27315789141108,"accuracy":0.63,"positive_recall":0.94,"specificity":0.32,"precision":0.5802469135802469,"balanced_accuracy":0.63,"f1":0.7175572519083969,"true_positive":47,"false_positive":34,"false_negative":3,"true_negative":16,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.09263156564431996,"baseline_adjusted_skill":0.26,"baseline_adjusted_score":0.26}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/logical_entailment / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.32800620595365,"accuracy":0.54,"positive_recall":0.1,"specificity":0.98,"precision":0.8333333333333334,"balanced_accuracy":0.54,"f1":0.17857142857142858,"true_positive":5,"false_positive":1,"false_negative":45,"true_negative":49,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.31202482381459995,"baseline_adjusted_skill":0.08000000000000007,"baseline_adjusted_score":0.08000000000000007}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/lonli / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.82,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.39,"baseline_adjusted_skill":0.7049180327868851,"baseline_adjusted_score":0.7049180327868851}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/massive / test · target_mass_at_prediction. Population 100 cases / 200 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.89,"uniform_accuracy_baseline":0.036111111111111115,"fixed_answer_accuracy_baseline":0.08833333333333333,"baseline_adjusted_skill":0.8793418647166362,"baseline_adjusted_score":0.8793418647166362}. Counts: {"cases": 100, "expected": 200, "succeeded": 200, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/mintaka-ja-boolean-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.23568898677845335,"accuracy":0.62,"positive_recall":0.6266666666666667,"specificity":0.6133333333333333,"precision":0.618421052631579,"balanced_accuracy":0.62,"f1":0.6225165562913907,"true_positive":94,"false_positive":58,"false_negative":56,"true_negative":92,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.057244052886186614,"baseline_adjusted_skill":0.24,"baseline_adjusted_score":0.24}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/miqa / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.95,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.56,"baseline_adjusted_skill":0.8863636363636362,"baseline_adjusted_score":0.8863636363636362}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/mmlu-prox-ja-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.4666666666666667,"uniform_accuracy_baseline":0.11021428571428572,"fixed_answer_accuracy_baseline":0.12554761904761905,"baseline_adjusted_skill":0.3900944808996107,"baseline_adjusted_score":0.3900944808996107}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/mmmlu-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.62,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.49333333333333335,"baseline_adjusted_score":0.49333333333333335}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/mtop / test · target_mass_at_prediction. Population 100 cases / 200 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.895,"uniform_accuracy_baseline":0.049879324215607396,"fixed_answer_accuracy_baseline":0.12442477876106194,"baseline_adjusted_skill":0.8800788356579745,"baseline_adjusted_score":0.8800788356579745}. Counts: {"cases": 100, "expected": 200, "succeeded": 200, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/mvtec-ad-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.22602053591649002,"accuracy":0.6366666666666667,"positive_recall":0.5462962962962963,"specificity":0.8690476190476191,"precision":0.9147286821705426,"balanced_accuracy":0.7076719576719577,"f1":0.6840579710144927,"true_positive":118,"false_positive":11,"false_negative":98,"true_negative":73,"positive_prevalence":0.72,"majority_accuracy_baseline":0.72,"constant_brier_baseline":0.2016,"brier_skill":-0.121133610696875,"baseline_adjusted_skill":0.41534391534391535,"baseline_adjusted_score":0.41534391534391535}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/nights-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.9,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.5033333333333333,"baseline_adjusted_skill":0.7986577181208054,"baseline_adjusted_score":0.7986577181208054}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/nlsat / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.25524134775286,"accuracy":0.51,"positive_recall":0.06,"specificity":0.96,"precision":0.6,"balanced_accuracy":0.51,"f1":0.10909090909090909,"true_positive":3,"false_positive":2,"false_negative":47,"true_negative":48,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.020965391011440015,"baseline_adjusted_skill":0.020000000000000018,"baseline_adjusted_score":0.020000000000000018}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/nlvr2-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.21031700942461,"accuracy":0.6833333333333333,"positive_recall":0.83125,"specificity":0.5142857142857142,"precision":0.6616915422885572,"balanced_accuracy":0.6727678571428571,"f1":0.7368421052631579,"true_positive":133,"false_positive":68,"false_negative":27,"true_negative":72,"positive_prevalence":0.5333333333333333,"majority_accuracy_baseline":0.5333333333333333,"constant_brier_baseline":0.2488888888888889,"brier_skill":0.15497630141897767,"baseline_adjusted_skill":0.3455357142857143,"baseline_adjusted_score":0.3455357142857143}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__amount-extraction-control-v1 / test · target_mass_at_prediction. Population 36 cases / 36 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.7777777777777778,"uniform_accuracy_baseline":0.23888888888888887,"fixed_answer_accuracy_baseline":0.2916666666666667,"baseline_adjusted_skill":0.6862745098039217,"baseline_adjusted_score":0.6862745098039217}. Counts: {"cases": 36, "expected": 36, "succeeded": 36, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 36

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__amount-extraction-control-v1 / test · binary_brier. Population 64 cases / 64 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.19440861839001564,"accuracy":0.703125,"positive_recall":0.875,"specificity":0.53125,"precision":0.6511627906976745,"balanced_accuracy":0.703125,"f1":0.7466666666666667,"true_positive":28,"false_positive":15,"false_negative":4,"true_negative":17,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.22236552643993746,"baseline_adjusted_skill":0.40625,"baseline_adjusted_score":0.40625}. Counts: {"cases": 64, "expected": 64, "succeeded": 64, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 64

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__browser-control-v1 / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":1,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.54,"baseline_adjusted_skill":1,"baseline_adjusted_score":1}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__citation-control-v1 / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.75,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.34,"baseline_adjusted_skill":0.6212121212121212,"baseline_adjusted_score":0.6212121212121212}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__context-retention-control-v1 / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.27948402953574997,"accuracy":0.6,"positive_recall":0.2,"specificity":1,"precision":1,"balanced_accuracy":0.6,"f1":0.3333333333333333,"true_positive":10,"false_positive":0,"false_negative":40,"true_negative":50,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.11793611814299987,"baseline_adjusted_skill":0.19999999999999996,"baseline_adjusted_score":0.19999999999999996}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__customer-control-v1 / test · target_mass_at_prediction. Population 17 cases / 17 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.8235294117647058,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.3235294117647059,"baseline_adjusted_skill":0.7391304347826085,"baseline_adjusted_score":0.7391304347826085}. Counts: {"cases": 17, "expected": 17, "succeeded": 17, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 17

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__customer-control-v1 / test · binary_brier. Population 33 cases / 33 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.34774601181048487,"accuracy":0.45454545454545453,"positive_recall":0.4375,"specificity":0.47058823529411764,"precision":0.4375,"balanced_accuracy":0.4540441176470588,"f1":0.4375,"true_positive":7,"false_positive":9,"false_negative":9,"true_negative":8,"positive_prevalence":0.48484848484848486,"majority_accuracy_baseline":0.5151515151515151,"constant_brier_baseline":0.2497704315886134,"brier_skill":-0.3922625252265368,"baseline_adjusted_skill":-0.09191176470588236,"baseline_adjusted_score":0}. Counts: {"cases": 33, "expected": 33, "succeeded": 33, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 33

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__customer-control-v1 / test · normalized_expected_score_mae. Population 50 cases / 50 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.1683400592464963,"normalized_score_rmse":0.30493964712309385,"constant_score_baseline":0.25,"constant_mae_baseline":0.33,"baseline_adjusted_skill":0.4898786083439506,"baseline_adjusted_score":0.4898786083439506}. Counts: {"cases": 50, "expected": 50, "succeeded": 50, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 50

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__drone-control-v1 / test · target_mass_at_prediction. Population 32 cases / 32 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.3125,"uniform_accuracy_baseline":0.178125,"fixed_answer_accuracy_baseline":0.2875,"baseline_adjusted_skill":0.03508771929824565,"baseline_adjusted_score":0.03508771929824565}. Counts: {"cases": 32, "expected": 32, "succeeded": 32, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 32

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__drone-control-v1 / test · binary_brier. Population 34 cases / 34 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.14575318502832355,"accuracy":0.6470588235294118,"positive_recall":0.29411764705882354,"specificity":1,"precision":1,"balanced_accuracy":0.6470588235294118,"f1":0.45454545454545453,"true_positive":5,"false_positive":0,"false_negative":12,"true_negative":17,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.4169872598867058,"baseline_adjusted_skill":0.2941176470588236,"baseline_adjusted_score":0.2941176470588236}. Counts: {"cases": 34, "expected": 34, "succeeded": 34, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 34

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__drone-control-v1 / test · normalized_expected_score_mae. Population 34 cases / 34 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.19999328546200104,"normalized_score_rmse":0.2738759207684412,"constant_score_baseline":0.5,"constant_mae_baseline":0.14705882352941177,"baseline_adjusted_skill":-0.35995434114160707,"baseline_adjusted_score":0}. Counts: {"cases": 34, "expected": 34, "succeeded": 34, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 34

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__email-selection-control-v1 / test · target_mass_at_prediction. Population 48 cases / 48 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.5208333333333334,"uniform_accuracy_baseline":0.13194444444444445,"fixed_answer_accuracy_baseline":0.6006944444444444,"baseline_adjusted_skill":-0.19999999999999984,"baseline_adjusted_score":0}. Counts: {"cases": 48, "expected": 48, "succeeded": 48, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 48

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__email-selection-control-v1 / test · binary_brier. Population 52 cases / 52 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.13558668684961536,"accuracy":0.8461538461538461,"positive_recall":0.9615384615384616,"specificity":0.7307692307692307,"precision":0.78125,"balanced_accuracy":0.8461538461538461,"f1":0.8620689655172413,"true_positive":25,"false_positive":7,"false_negative":1,"true_negative":19,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.45765325260153855,"baseline_adjusted_skill":0.6923076923076923,"baseline_adjusted_score":0.6923076923076923}. Counts: {"cases": 52, "expected": 52, "succeeded": 52, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 52

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__entity-alignment-control-v1 / test · binary_brier. Population 75 cases / 75 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.09064572627306668,"accuracy":0.8666666666666667,"positive_recall":1,"specificity":0.7222222222222222,"precision":0.7959183673469388,"balanced_accuracy":0.8611111111111112,"f1":0.8863636363636364,"true_positive":39,"false_positive":10,"false_negative":0,"true_negative":26,"positive_prevalence":0.52,"majority_accuracy_baseline":0.52,"constant_brier_baseline":0.24960000000000004,"brier_skill":0.636836032559829,"baseline_adjusted_skill":0.7222222222222223,"baseline_adjusted_score":0.7222222222222223}. Counts: {"cases": 75, "expected": 75, "succeeded": 75, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 75

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__entity-alignment-control-v1 / test · normalized_expected_score_mae. Population 25 cases / 25 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.3162689244818223,"normalized_score_rmse":0.39089194268906513,"constant_score_baseline":0.5,"constant_mae_baseline":0.28,"baseline_adjusted_skill":-0.12953187314936532,"baseline_adjusted_score":0}. Counts: {"cases": 25, "expected": 25, "succeeded": 25, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 25

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__ir-control-v1 / test · target_mass_at_prediction. Population 17 cases / 17 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.7647058823529411,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.2647058823529412,"baseline_adjusted_skill":0.6799999999999998,"baseline_adjusted_score":0.6799999999999998}. Counts: {"cases": 17, "expected": 17, "succeeded": 17, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 17

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__ir-control-v1 / test · binary_brier. Population 28 cases / 28 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.2378128659075,"accuracy":0.7142857142857143,"positive_recall":0.9285714285714286,"specificity":0.5,"precision":0.65,"balanced_accuracy":0.7142857142857143,"f1":0.7647058823529411,"true_positive":13,"false_positive":7,"false_negative":1,"true_negative":7,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.048748536369999984,"baseline_adjusted_skill":0.4285714285714286,"baseline_adjusted_score":0.4285714285714286}. Counts: {"cases": 28, "expected": 28, "succeeded": 28, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 28

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__ir-control-v1 / test · normalized_expected_score_mae. Population 55 cases / 55 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.25444572681323885,"normalized_score_rmse":0.3503103669129615,"constant_score_baseline":0.3333333333333333,"constant_mae_baseline":0.1696969696969697,"baseline_adjusted_skill":-0.49941231872087166,"baseline_adjusted_score":0}. Counts: {"cases": 55, "expected": 55, "succeeded": 55, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 55

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__mailroom-control-v1 / test · target_mass_at_prediction. Population 15 cases / 15 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":1,"uniform_accuracy_baseline":0.15555555555555553,"fixed_answer_accuracy_baseline":0.2,"baseline_adjusted_skill":1,"baseline_adjusted_score":1}. Counts: {"cases": 15, "expected": 15, "succeeded": 15, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 15

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__mailroom-control-v1 / test · binary_brier. Population 85 cases / 85 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.10421170471099998,"accuracy":0.8470588235294118,"positive_recall":0.9333333333333333,"specificity":0.75,"precision":0.8076923076923077,"balanced_accuracy":0.8416666666666667,"f1":0.865979381443299,"true_positive":42,"false_positive":10,"false_negative":3,"true_negative":30,"positive_prevalence":0.5294117647058824,"majority_accuracy_baseline":0.5294117647058824,"constant_brier_baseline":0.2491349480968858,"brier_skill":0.5817057963683473,"baseline_adjusted_skill":0.6833333333333333,"baseline_adjusted_score":0.6833333333333333}. Counts: {"cases": 85, "expected": 85, "succeeded": 85, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 85

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__painting-geometry-v1 / test · target_mass_at_prediction. Population 25 cases / 25 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.92,"uniform_accuracy_baseline":0.07805555555555556,"fixed_answer_accuracy_baseline":0.24,"baseline_adjusted_skill":0.8947368421052632,"baseline_adjusted_score":0.8947368421052632}. Counts: {"cases": 25, "expected": 25, "succeeded": 25, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 25

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__painting-geometry-v1 / test · binary_brier. Population 50 cases / 50 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.26152834449796,"accuracy":0.68,"positive_recall":0.5714285714285714,"specificity":0.9333333333333333,"precision":0.9523809523809523,"balanced_accuracy":0.7523809523809524,"f1":0.7142857142857143,"true_positive":20,"false_positive":1,"false_negative":15,"true_negative":14,"positive_prevalence":0.7,"majority_accuracy_baseline":0.7,"constant_brier_baseline":0.21,"brier_skill":-0.2453730690379048,"baseline_adjusted_skill":0.5047619047619047,"baseline_adjusted_score":0.5047619047619047}. Counts: {"cases": 50, "expected": 50, "succeeded": 50, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 50

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__painting-geometry-v1 / test · normalized_expected_score_mae. Population 25 cases / 25 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.1797271414441774,"normalized_score_rmse":0.314655506807372,"constant_score_baseline":0.5,"constant_mae_baseline":0.28,"baseline_adjusted_skill":0.35811735198508077,"baseline_adjusted_score":0.35811735198508077}. Counts: {"cases": 25, "expected": 25, "succeeded": 25, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 25

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__phone-extraction-control-v1 / test · target_mass_at_prediction. Population 79 cases / 79 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.6835443037974683,"uniform_accuracy_baseline":0.24240506329113923,"fixed_answer_accuracy_baseline":0.4177215189873418,"baseline_adjusted_skill":0.45652173913043476,"baseline_adjusted_score":0.45652173913043476}. Counts: {"cases": 79, "expected": 79, "succeeded": 79, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 79

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__phone-extraction-control-v1 / test · binary_brier. Population 21 cases / 21 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.0874048831612381,"accuracy":0.8571428571428571,"positive_recall":1,"specificity":0.7,"precision":0.7857142857142857,"balanced_accuracy":0.85,"f1":0.88,"true_positive":11,"false_positive":3,"false_negative":0,"true_negative":7,"positive_prevalence":0.5238095238095238,"majority_accuracy_baseline":0.5238095238095238,"constant_brier_baseline":0.2494331065759637,"brier_skill":0.6495858775081272,"baseline_adjusted_skill":0.7,"baseline_adjusted_score":0.7}. Counts: {"cases": 21, "expected": 21, "succeeded": 21, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 21

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__reasoning-control-v1 / test · target_mass_at_prediction. Population 33 cases / 33 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.7878787878787878,"uniform_accuracy_baseline":0.32373737373737377,"fixed_answer_accuracy_baseline":0.3939393939393939,"baseline_adjusted_skill":0.6499999999999999,"baseline_adjusted_score":0.6499999999999999}. Counts: {"cases": 33, "expected": 33, "succeeded": 33, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 33

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__reasoning-control-v1 / test · binary_brier. Population 33 cases / 33 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.22986726921124243,"accuracy":0.6666666666666666,"positive_recall":0.47058823529411764,"specificity":0.875,"precision":0.8,"balanced_accuracy":0.6727941176470589,"f1":0.5925925925925926,"true_positive":8,"false_positive":2,"false_negative":9,"true_negative":14,"positive_prevalence":0.5151515151515151,"majority_accuracy_baseline":0.5151515151515151,"constant_brier_baseline":0.2497704315886134,"brier_skill":0.07968582290057713,"baseline_adjusted_skill":0.34558823529411775,"baseline_adjusted_score":0.34558823529411775}. Counts: {"cases": 33, "expected": 33, "succeeded": 33, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 33

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__reasoning-control-v1 / test · normalized_expected_score_mae. Population 34 cases / 34 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.26025380296351486,"normalized_score_rmse":0.3365009495441011,"constant_score_baseline":0.7083333333333333,"constant_mae_baseline":0.3431372549019608,"baseline_adjusted_skill":0.24154605993489953,"baseline_adjusted_score":0.24154605993489953}. Counts: {"cases": 34, "expected": 34, "succeeded": 34, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 34

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__silent-failure-control-v1 / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.38110145459350003,"accuracy":0.41,"positive_recall":0.46,"specificity":0.36,"precision":0.41818181818181815,"balanced_accuracy":0.41000000000000003,"f1":0.4380952380952381,"true_positive":23,"false_positive":32,"false_negative":27,"true_negative":18,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.5244058183740001,"baseline_adjusted_skill":-0.17999999999999994,"baseline_adjusted_score":0}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__snake-v1 / test · target_mass_at_prediction. Population 25 cases / 25 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.29333333333333333,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.35333333333333333,"baseline_adjusted_skill":-0.09278350515463916,"baseline_adjusted_score":0}. Counts: {"cases": 25, "expected": 25, "succeeded": 25, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 25

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__snake-v1 / test · binary_brier. Population 75 cases / 75 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.25327556578588,"accuracy":0.6266666666666667,"positive_recall":0.8378378378378378,"specificity":0.42105263157894735,"precision":0.5849056603773585,"balanced_accuracy":0.6294452347083925,"f1":0.6888888888888889,"true_positive":31,"false_positive":22,"false_negative":6,"true_negative":16,"positive_prevalence":0.49333333333333335,"majority_accuracy_baseline":0.5066666666666666,"constant_brier_baseline":0.24995555555555554,"brier_skill":-0.013282402237251079,"baseline_adjusted_skill":0.25889046941678506,"baseline_adjusted_score":0.25889046941678506}. Counts: {"cases": 75, "expected": 75, "succeeded": 75, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 75

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__sponsor-segment-control-v1 / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.94,"uniform_accuracy_baseline":0.14285714285714285,"fixed_answer_accuracy_baseline":0.22,"baseline_adjusted_skill":0.923076923076923,"baseline_adjusted_score":0.923076923076923}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__tic_tac_toe-v1 / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.345,"uniform_accuracy_baseline":0.32416666666666666,"fixed_answer_accuracy_baseline":0.34,"baseline_adjusted_skill":0.0075757575757575,"baseline_adjusted_score":0.0075757575757575}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__vizdoom-basic-v1 / test · binary_brier. Population 33 cases / 33 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.12420045782751514,"accuracy":0.8484848484848485,"positive_recall":1,"specificity":0.7058823529411765,"precision":0.7619047619047619,"balanced_accuracy":0.8529411764705883,"f1":0.8648648648648649,"true_positive":16,"false_positive":5,"false_negative":0,"true_negative":12,"positive_prevalence":0.48484848484848486,"majority_accuracy_baseline":0.5151515151515151,"constant_brier_baseline":0.2497704315886134,"brier_skill":0.5027415493596912,"baseline_adjusted_skill":0.7058823529411766,"baseline_adjusted_score":0.7058823529411766}. Counts: {"cases": 33, "expected": 33, "succeeded": 33, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 33

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__vizdoom-basic-v1 / test · normalized_expected_score_mae. Population 33 cases / 33 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.13259481347221602,"normalized_score_rmse":0.15208254576907537,"constant_score_baseline":0.5,"constant_mae_baseline":0.2196969696969697,"baseline_adjusted_skill":0.3964649869540512,"baseline_adjusted_score":0.3964649869540512}. Counts: {"cases": 33, "expected": 33, "succeeded": 33, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 33

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__workflow-controls-v1__agent_trace_observability / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.1539330293097,"accuracy":0.78,"positive_recall":0.5454545454545454,"specificity":0.8461538461538461,"precision":0.5,"balanced_accuracy":0.6958041958041958,"f1":0.5217391304347826,"true_positive":12,"false_positive":12,"false_negative":10,"true_negative":66,"positive_prevalence":0.22,"majority_accuracy_baseline":0.78,"constant_brier_baseline":0.1716,"brier_skill":0.102954374652098,"baseline_adjusted_skill":0.39160839160839167,"baseline_adjusted_score":0.39160839160839167}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__workflow-controls-v1__customer_service / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.12212800130743,"accuracy":0.85,"positive_recall":0.7297297297297297,"specificity":0.9206349206349206,"precision":0.84375,"balanced_accuracy":0.8251823251823251,"f1":0.782608695652174,"true_positive":27,"false_positive":5,"false_negative":10,"true_negative":58,"positive_prevalence":0.37,"majority_accuracy_baseline":0.63,"constant_brier_baseline":0.23310000000000003,"brier_skill":0.47607035046147583,"baseline_adjusted_skill":0.6503646503646503,"baseline_adjusted_score":0.6503646503646503}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__workflow-controls-v1__invoice_processing / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.11927396224857001,"accuracy":0.79,"positive_recall":0.6153846153846154,"specificity":0.9016393442622951,"precision":0.8,"balanced_accuracy":0.7585119798234552,"f1":0.6956521739130435,"true_positive":24,"false_positive":6,"false_negative":15,"true_negative":55,"positive_prevalence":0.39,"majority_accuracy_baseline":0.61,"constant_brier_baseline":0.2379,"brier_skill":0.4986382419143758,"baseline_adjusted_skill":0.5170239596469104,"baseline_adjusted_score":0.5170239596469104}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/open_jev__workflow-controls-v1__security_incidents / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.05326642182447,"accuracy":0.93,"positive_recall":0.8709677419354839,"specificity":0.9565217391304348,"precision":0.9,"balanced_accuracy":0.9137447405329593,"f1":0.8852459016393442,"true_positive":27,"false_positive":3,"false_negative":4,"true_negative":66,"positive_prevalence":0.31,"majority_accuracy_baseline":0.69,"constant_brier_baseline":0.21389999999999998,"brier_skill":0.7509751200352033,"baseline_adjusted_skill":0.8274894810659186,"baseline_adjusted_score":0.8274894810659186}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/openbookqa / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.91,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.28,"baseline_adjusted_skill":0.875,"baseline_adjusted_score":0.875}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/patent_similarity / test · normalized_expected_score_mae. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.17967286581702233,"normalized_score_rmse":0.22818516669127717,"constant_score_baseline":0.25,"constant_mae_baseline":0.2325,"baseline_adjusted_skill":0.22721348035689326,"baseline_adjusted_score":0.22721348035689326}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/paws / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.1247360124919,"accuracy":0.83,"positive_recall":0.9,"specificity":0.76,"precision":0.7894736842105263,"balanced_accuracy":0.8300000000000001,"f1":0.8411214953271028,"true_positive":45,"false_positive":12,"false_negative":5,"true_negative":38,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.5010559500324,"baseline_adjusted_skill":0.6600000000000001,"baseline_adjusted_score":0.6600000000000001}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/plane / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.28938144239683,"accuracy":0.52,"positive_recall":0.68,"specificity":0.36,"precision":0.5151515151515151,"balanced_accuracy":0.52,"f1":0.5862068965517241,"true_positive":34,"false_positive":32,"false_negative":16,"true_negative":18,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.15752576958732,"baseline_adjusted_skill":0.040000000000000036,"baseline_adjusted_score":0.040000000000000036}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/poem_sentiment / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.65,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.65,"baseline_adjusted_skill":0,"baseline_adjusted_score":0}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/pope-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.09684425278528,"accuracy":0.8766666666666667,"positive_recall":0.7666666666666667,"specificity":0.9866666666666667,"precision":0.9829059829059829,"balanced_accuracy":0.8766666666666667,"f1":0.8614232209737828,"true_positive":115,"false_positive":2,"false_negative":35,"true_negative":148,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.61262298885888,"baseline_adjusted_skill":0.7533333333333334,"baseline_adjusted_score":0.7533333333333334}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/qasper / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.09230689937291,"accuracy":0.85,"positive_recall":0.9,"specificity":0.8,"precision":0.8181818181818182,"balanced_accuracy":0.8500000000000001,"f1":0.8571428571428571,"true_positive":45,"false_positive":10,"false_negative":5,"true_negative":40,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.63077240250836,"baseline_adjusted_skill":0.7000000000000002,"baseline_adjusted_score":0.7000000000000002}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/quartz / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.92,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.58,"baseline_adjusted_skill":0.8095238095238096,"baseline_adjusted_score":0.8095238095238096}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/robust_lr / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.78,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.4,"baseline_adjusted_skill":0.6333333333333334,"baseline_adjusted_score":0.6333333333333334}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/ruletaker / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.1652326689718,"accuracy":0.76,"positive_recall":0.58,"specificity":0.94,"precision":0.90625,"balanced_accuracy":0.76,"f1":0.7073170731707317,"true_positive":29,"false_positive":3,"false_negative":21,"true_negative":47,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.3390693241128,"baseline_adjusted_skill":0.52,"baseline_adjusted_score":0.52}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/rvlcdip-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.6633333333333333,"uniform_accuracy_baseline":0.0625,"fixed_answer_accuracy_baseline":0.10666666666666667,"baseline_adjusted_skill":0.6231343283582089,"baseline_adjusted_score":0.6231343283582089}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/s1mb-generalization-contextual-choice / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.99,"uniform_accuracy_baseline":0.20851190476190473,"fixed_answer_accuracy_baseline":0.22333333333333333,"baseline_adjusted_skill":0.9871244635193133,"baseline_adjusted_score":0.9871244635193133}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/s1mb-generalization-contextual-noul / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.04504831868412,"accuracy":0.95,"positive_recall":0.96,"specificity":0.94,"precision":0.9411764705882353,"balanced_accuracy":0.95,"f1":0.9504950495049505,"true_positive":48,"false_positive":3,"false_negative":2,"true_negative":47,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.8198067252635199,"baseline_adjusted_skill":0.8999999999999999,"baseline_adjusted_score":0.8999999999999999}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/s1mb-generalization-contextual-score / test · normalized_expected_score_mae. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.11872385153133452,"normalized_score_rmse":0.18086253563495397,"constant_score_baseline":0.5,"constant_mae_baseline":0.3,"baseline_adjusted_skill":0.604253828228885,"baseline_adjusted_score":0.604253828228885}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/s1mb-generalization-diverse-choice / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.93,"uniform_accuracy_baseline":0.22851190476190475,"fixed_answer_accuracy_baseline":0.24333333333333332,"baseline_adjusted_skill":0.907488986784141,"baseline_adjusted_score":0.907488986784141}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/s1mb-generalization-diverse-noul / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.043316378115819995,"accuracy":0.93,"positive_recall":0.94,"specificity":0.92,"precision":0.9215686274509803,"balanced_accuracy":0.9299999999999999,"f1":0.9306930693069307,"true_positive":47,"false_positive":4,"false_negative":3,"true_negative":46,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.82673448753672,"baseline_adjusted_skill":0.8599999999999999,"baseline_adjusted_score":0.8599999999999999}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/s1mb-generalization-diverse-score / test · normalized_expected_score_mae. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.09526931113187864,"normalized_score_rmse":0.15505257163111016,"constant_score_baseline":0.4222222222222222,"constant_mae_baseline":0.3042222222222222,"baseline_adjusted_skill":0.6868430240369219,"baseline_adjusted_score":0.6868430240369219}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/scicite / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.76,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.38,"baseline_adjusted_skill":0.6129032258064516,"baseline_adjusted_score":0.6129032258064516}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/scienceqa-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.9533333333333334,"uniform_accuracy_baseline":0.3467777777777778,"fixed_answer_accuracy_baseline":0.36,"baseline_adjusted_skill":0.9270833333333334,"baseline_adjusted_score":0.9270833333333334}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/scitail / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.05707549509357,"accuracy":0.93,"positive_recall":0.94,"specificity":0.92,"precision":0.9215686274509803,"balanced_accuracy":0.9299999999999999,"f1":0.9306930693069307,"true_positive":47,"false_positive":4,"false_negative":3,"true_negative":46,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.7716980196257199,"baseline_adjusted_skill":0.8599999999999999,"baseline_adjusted_score":0.8599999999999999}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/scone / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.91,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.5,"baseline_adjusted_skill":0.8200000000000001,"baseline_adjusted_score":0.8200000000000001}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/sdoh_nli / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.06394858954761999,"accuracy":0.92,"positive_recall":0.88,"specificity":0.96,"precision":0.9565217391304348,"balanced_accuracy":0.9199999999999999,"f1":0.9166666666666666,"true_positive":44,"false_positive":2,"false_negative":6,"true_negative":48,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.74420564180952,"baseline_adjusted_skill":0.8399999999999999,"baseline_adjusted_score":0.8399999999999999}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/sgd / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.57,"uniform_accuracy_baseline":0.3533333333333333,"fixed_answer_accuracy_baseline":0.41,"baseline_adjusted_skill":0.27118644067796605,"baseline_adjusted_score":0.27118644067796605}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/snli / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.9,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.38,"baseline_adjusted_skill":0.8387096774193549,"baseline_adjusted_score":0.8387096774193549}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/sobaco-culture-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.44666666666666666,"uniform_accuracy_baseline":0.3333333333333333,"fixed_answer_accuracy_baseline":0.3333333333333333,"baseline_adjusted_skill":0.16999999999999998,"baseline_adjusted_score":0.16999999999999998}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/spartqa / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.45,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.38,"baseline_adjusted_skill":0.11290322580645162,"baseline_adjusted_score":0.11290322580645162}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/stepgame / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.39,"uniform_accuracy_baseline":0.1111111111111111,"fixed_answer_accuracy_baseline":0.16,"baseline_adjusted_skill":0.27380952380952384,"baseline_adjusted_score":0.27380952380952384}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/sugarcrepe-choice / test · target_mass_at_prediction. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.94,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.58,"baseline_adjusted_skill":0.857142857142857,"baseline_adjusted_score":0.857142857142857}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoArguAna / test · binary_brier. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.16731323849263,"accuracy":0.568125,"positive_recall":0.6005273566249176,"specificity":0.5605429585068641,"precision":0.24228723404255317,"balanced_accuracy":0.5805351575658908,"f1":0.3452719348114459,"true_positive":45.55,"false_positive":142.45,"false_negative":30.3,"true_negative":181.7,"positive_prevalence":0.189625,"majority_accuracy_baseline":0.8103750000000001,"constant_brier_baseline":0.07612360937500001,"brier_skill":-1.1979152048402195,"baseline_adjusted_skill":0.1610703151317816,"baseline_adjusted_score":0.1610703151317816}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoArguAna / test · normalized_expected_score_mae. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.3061242789475336,"normalized_score_rmse":0.3625092133014206,"constant_score_baseline":0,"constant_mae_baseline":0.21375,"baseline_adjusted_skill":-0.4321603693451863,"baseline_adjusted_score":0}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoDBPedia / test · binary_brier. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.07040803509290999,"accuracy":0.7923749999999999,"positive_recall":0.5232067510548523,"specificity":0.8902335094596898,"precision":0.634090909090909,"balanced_accuracy":0.706720130257271,"f1":0.5733367582840996,"true_positive":55.8,"false_positive":32.2,"false_negative":50.85,"true_negative":261.15,"positive_prevalence":0.266625,"majority_accuracy_baseline":0.733375,"constant_brier_baseline":0.115654859375,"brier_skill":0.3912228550240283,"baseline_adjusted_skill":0.41344026051454197,"baseline_adjusted_score":0.41344026051454197}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoDBPedia / test · normalized_expected_score_mae. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.19130109826208958,"normalized_score_rmse":0.2438982188521061,"constant_score_baseline":0.25,"constant_mae_baseline":0.26875,"baseline_adjusted_skill":0.2881819599550155,"baseline_adjusted_score":0.2881819599550155}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoFiQA2018 / test · binary_brier. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.05118737496881,"accuracy":0.8036249999999999,"positive_recall":0.5914988814317673,"specificity":0.8858629661751951,"precision":0.6676767676767676,"balanced_accuracy":0.7386809238034813,"f1":0.6272835112692764,"true_positive":66.1,"false_positive":32.9,"false_negative":45.65,"true_negative":255.35,"positive_prevalence":0.279375,"majority_accuracy_baseline":0.7206250000000001,"constant_brier_baseline":0.11315585937500001,"brier_skill":0.5476383171712358,"baseline_adjusted_skill":0.47736184760696254,"baseline_adjusted_score":0.47736184760696254}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoFiQA2018 / test · normalized_expected_score_mae. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.17305936676172706,"normalized_score_rmse":0.22011644655844548,"constant_score_baseline":0.25,"constant_mae_baseline":0.264375,"baseline_adjusted_skill":0.34540192241427126,"baseline_adjusted_score":0.34540192241427126}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoHotpotQA / test · binary_brier. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.070130005309085,"accuracy":0.826875,"positive_recall":0.28450704225352114,"specificity":0.9815261044176706,"precision":0.8145161290322581,"balanced_accuracy":0.6330165733355959,"f1":0.42171189979123175,"true_positive":25.25,"false_positive":5.75,"false_negative":63.5,"true_negative":305.5,"positive_prevalence":0.221875,"majority_accuracy_baseline":0.778125,"constant_brier_baseline":0.12674023437499998,"brier_skill":0.44666343994927604,"baseline_adjusted_skill":0.2660331466711918,"baseline_adjusted_score":0.2660331466711918}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoHotpotQA / test · normalized_expected_score_mae. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.1591673413905175,"normalized_score_rmse":0.22669431501077364,"constant_score_baseline":0,"constant_mae_baseline":0.225625,"baseline_adjusted_skill":0.2945491794326094,"baseline_adjusted_score":0.2945491794326094}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoMSMARCO / test · binary_brier. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.03658571322976,"accuracy":0.8482500000000001,"positive_recall":0.7188090737240076,"specificity":0.8947994561522774,"precision":0.7107476635514018,"balanced_accuracy":0.8068042649381425,"f1":0.7147556390977444,"true_positive":76.05,"false_positive":30.95,"false_negative":29.75,"true_negative":263.25,"positive_prevalence":0.2645,"majority_accuracy_baseline":0.7355,"constant_brier_baseline":0.11362725,"brier_skill":0.6780199007741541,"baseline_adjusted_skill":0.613608529876285,"baseline_adjusted_score":0.613608529876285}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoMSMARCO / test · normalized_expected_score_mae. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.16417329983817253,"normalized_score_rmse":0.21108214190050859,"constant_score_baseline":0.25,"constant_mae_baseline":0.25125,"baseline_adjusted_skill":0.3465739309923481,"baseline_adjusted_score":0.3465739309923481}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoNFCorpus / test · binary_brier. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.0580983823367775,"accuracy":0.83575,"positive_recall":0.43668407310704965,"specificity":0.9302721088435374,"precision":0.5973214285714287,"balanced_accuracy":0.6834780909752936,"f1":0.5045248868778281,"true_positive":33.45,"false_positive":22.55,"false_negative":43.15,"true_negative":300.85,"positive_prevalence":0.19149999999999998,"majority_accuracy_baseline":0.8085,"constant_brier_baseline":0.09190274999999999,"brier_skill":0.36782759670654575,"baseline_adjusted_skill":0.3669561819505871,"baseline_adjusted_score":0.3669561819505871}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoNFCorpus / test · normalized_expected_score_mae. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.1606506088497699,"normalized_score_rmse":0.21304627930347764,"constant_score_baseline":0,"constant_mae_baseline":0.206875,"baseline_adjusted_skill":0.22344116568087058,"baseline_adjusted_score":0.22344116568087058}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoNQ / test · binary_brier. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.042940760189655,"accuracy":0.8927499999999999,"positive_recall":0.6226287262872628,"specificity":0.953862660944206,"precision":0.7532786885245902,"balanced_accuracy":0.7882456936157345,"f1":0.6817507418397626,"true_positive":45.95,"false_positive":15.05,"false_negative":27.85,"true_negative":311.15,"positive_prevalence":0.1845,"majority_accuracy_baseline":0.8155,"constant_brier_baseline":0.10922225,"brier_skill":0.6068497015062866,"baseline_adjusted_skill":0.576491387231469,"baseline_adjusted_score":0.576491387231469}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoNQ / test · normalized_expected_score_mae. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.16445485506324423,"normalized_score_rmse":0.22292001901176198,"constant_score_baseline":0,"constant_mae_baseline":0.189375,"baseline_adjusted_skill":0.1315915244185123,"baseline_adjusted_score":0.1315915244185123}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoSCIDOCS / test · binary_brier. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.069152160647605,"accuracy":0.825,"positive_recall":0.12420382165605096,"specificity":0.9961119751166407,"precision":0.8863636363636364,"balanced_accuracy":0.5601578983863459,"f1":0.21787709497206703,"true_positive":9.75,"false_positive":1.25,"false_negative":68.75,"true_negative":320.25,"positive_prevalence":0.19625,"majority_accuracy_baseline":0.80375,"constant_brier_baseline":0.09878593749999999,"brier_skill":0.29997970968686705,"baseline_adjusted_skill":0.12031579677269177,"baseline_adjusted_score":0.12031579677269177}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoSCIDOCS / test · normalized_expected_score_mae. Population 400 cases / 400 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.17796267524812348,"normalized_score_rmse":0.2418338164231125,"constant_score_baseline":0,"constant_mae_baseline":0.21125,"baseline_adjusted_skill":0.15757313492012548,"baseline_adjusted_score":0.15757313492012548}. Counts: {"cases": 400, "expected": 400, "succeeded": 400, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 400

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoTouche2020 / test · binary_brier. Population 392 cases / 392 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.07775821224592602,"accuracy":0.6992346938775511,"positive_recall":0.8502372479240806,"specificity":0.5852730528200538,"precision":0.6074152542372881,"balanced_accuracy":0.7177551503720672,"f1":0.7086010874938211,"true_positive":143.35,"false_positive":92.64999999999999,"false_negative":25.25,"true_negative":130.75,"positive_prevalence":0.4301020408163265,"majority_accuracy_baseline":0.5698979591836735,"constant_brier_baseline":0.12359641815910039,"brier_skill":0.3708700186939786,"baseline_adjusted_skill":0.4355103007441343,"baseline_adjusted_score":0.4355103007441343}. Counts: {"cases": 392, "expected": 392, "succeeded": 392, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 392

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanobeir__NanoTouche2020 / test · normalized_expected_score_mae. Population 392 cases / 392 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.20226350294690043,"normalized_score_rmse":0.26060148281769346,"constant_score_baseline":0.5,"constant_mae_baseline":0.2755102040816326,"baseline_adjusted_skill":0.2658583967112502,"baseline_adjusted_score":0.2658583967112502}. Counts: {"cases": 392, "expected": 392, "succeeded": 392, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 392

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanocoir / test · binary_brier. Population 800 cases / 800 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.048791202343911245,"accuracy":0.8941250000000001,"positive_recall":0.6152635719905587,"specificity":0.9467974438995393,"precision":0.6859649122807018,"balanced_accuracy":0.781030507945049,"f1":0.6486934881791788,"true_positive":78.2,"false_positive":35.8,"false_negative":48.9,"true_negative":637.1,"positive_prevalence":0.158875,"majority_accuracy_baseline":0.841125,"constant_brier_baseline":0.09877748437499999,"brier_skill":0.5060493527180774,"baseline_adjusted_skill":0.562061015890098,"baseline_adjusted_score":0.562061015890098}. Counts: {"cases": 800, "expected": 800, "succeeded": 800, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 800

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/synthetic_relevance__nanocoir / test · normalized_expected_score_mae. Population 800 cases / 800 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.1770066635922726,"normalized_score_rmse":0.23068909976949228,"constant_score_baseline":0,"constant_mae_baseline":0.165,"baseline_adjusted_skill":-0.07276765813498542,"baseline_adjusted_score":0}. Counts: {"cases": 800, "expected": 800, "succeeded": 800, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 800

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/tallyqa-score / test · normalized_expected_score_mae. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.04760530145253258,"normalized_score_rmse":0.08942712151171783,"constant_score_baseline":0.1111111111111111,"constant_mae_baseline":0.10629629629629629,"baseline_adjusted_skill":0.5521452476591011,"baseline_adjusted_score":0.5521452476591011}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/temporal_nli / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.54,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.38,"baseline_adjusted_skill":0.2580645161290323,"baseline_adjusted_score":0.2580645161290323}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/tracie / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.26996729949084,"accuracy":0.6,"positive_recall":0.38,"specificity":0.82,"precision":0.6785714285714286,"balanced_accuracy":0.6,"f1":0.48717948717948717,"true_positive":19,"false_positive":9,"false_negative":31,"true_negative":41,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.0798691979633599,"baseline_adjusted_skill":0.19999999999999996,"baseline_adjusted_score":0.19999999999999996}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/ud_ewt / test · target_mass_at_prediction. Population 100 cases / 1509 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.38303512259774686,"uniform_accuracy_baseline":0.058823529411764705,"fixed_answer_accuracy_baseline":0.14910536779324055,"baseline_adjusted_skill":0.2749221183800623,"baseline_adjusted_score":0.2749221183800623}. Counts: {"cases": 100, "expected": 1509, "succeeded": 1509, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/visa-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.30719451126827,"accuracy":0.5166666666666667,"positive_recall":0.16666666666666666,"specificity":1,"precision":1,"balanced_accuracy":0.5833333333333334,"f1":0.2857142857142857,"true_positive":29,"false_positive":0,"false_negative":145,"true_negative":126,"positive_prevalence":0.58,"majority_accuracy_baseline":0.58,"constant_brier_baseline":0.24359999999999998,"brier_skill":-0.2610612121029148,"baseline_adjusted_skill":0.16666666666666674,"baseline_adjusted_score":0.16666666666666674}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/vsr-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.18930059500078666,"accuracy":0.7266666666666667,"positive_recall":0.7452229299363057,"specificity":0.7062937062937062,"precision":0.7358490566037735,"balanced_accuracy":0.725758318115006,"f1":0.740506329113924,"true_positive":117,"false_positive":42,"false_negative":40,"true_negative":101,"positive_prevalence":0.5233333333333333,"majority_accuracy_baseline":0.5233333333333333,"constant_brier_baseline":0.24945555555555557,"brier_skill":0.24114500244662607,"baseline_adjusted_skill":0.45151663623001204,"baseline_adjusted_score":0.45151663623001204}. Counts: {"cases": 300, "expected": 300, "succeeded": 300, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 300

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/winobias / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.87,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.54,"baseline_adjusted_skill":0.717391304347826,"baseline_adjusted_score":0.717391304347826}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/winowhy / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.23208197381103,"accuracy":0.63,"positive_recall":0.66,"specificity":0.6,"precision":0.6226415094339622,"balanced_accuracy":0.63,"f1":0.6407766990291263,"true_positive":33,"false_positive":20,"false_negative":17,"true_negative":30,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.07167210475588004,"baseline_adjusted_skill":0.26,"baseline_adjusted_score":0.26}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB datasets/wiqa / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-4B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-4B.

Published measured S1MB run; community execution/submission status is not assumed independent. Choice is target mass at the selected option; soft targets are not ordinary hard-label accuracy. All published diagnostics: {"target_mass_at_prediction":0.53,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.37,"baseline_adjusted_skill":0.253968253968254,"baseline_adjusted_score":0.253968253968254}. Counts: {"cases": 100, "expected": 100, "succeeded": 100, "failed": 0, "abstained": 0}. Parameter-count conventions excluding lookup/embedding parameters are not model MoE active counts. No executed weight SHA is stated in this display record; exact named repository and adapter are retained.

Pinned public display snapshot 2026-10-17T12:53:13.764Z. Benchmark definitions keep dataset/split and task semantics. Native binary Brier and normalized expected-score MAE are errors, not percents. Failed, partial or missing results never become zero.

Checked / reported: 2026-10-18 · Samples: 100

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB english-v1 · BordaScore

Published english-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 137 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB english-v1 · TaskAvg

Published english-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 137 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB english-v1 · Noul

Published english-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 137 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB english-v1 · Choice

Published english-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 137 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB english-v1 · Score

Published english-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 137 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB english-v1 · GeneralNoul

Published english-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 137 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB english-v1 · GeneralChoice

Published english-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 137 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB english-v1 · GeneralScore

Published english-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 137 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB japanese-v1 · BordaScore

Published japanese-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 27 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB japanese-v1 · TaskAvg

Published japanese-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 27 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB japanese-v1 · Noul

Published japanese-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 27 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB japanese-v1 · Choice

Published japanese-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 27 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB japanese-v1 · Score

Published japanese-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 27 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB japanese-v1 · GeneralNoul

Published japanese-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 27 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB japanese-v1 · GeneralChoice

Published japanese-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 27 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB japanese-v1 · GeneralScore

Published japanese-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 27 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB vision-v1 · BordaScore

Published vision-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 20 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB vision-v1 · TaskAvg

Published vision-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 20 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB vision-v1 · Noul

Published vision-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 20 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB vision-v1 · Choice

Published vision-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 20 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB vision-v1 · Score

Published vision-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 20 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB vision-v1 · GeneralNoul

Published vision-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 20 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB vision-v1 · GeneralChoice

Published vision-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 20 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified

S1MB vision-v1 · GeneralScore

Published vision-v1 UI scope; OneJev 1.6 4BOmniJev/OneJev1.6-4B.

Coverage 20 benchmarks. Read the source scoring specification for adjustment, clipping and scope exclusions.

Value read from the publisher’s rendered table, not recomputed from rounded components. Noul/Choice/Score and General columns are source baseline-adjusted scores. Borda is relative to the complete model cohort in this dated scope; TaskAvg is equal task weight after equal benchmark weight. Neither is native accuracy/Brier/MAE.

Checked / reported: 2026-10-18 · Samples: Not published

Snapshot: 2026-10-17T12:53:13.764Z · Revision: 706ef6637478b78e908be90088f68d8c8f0d52e4 · Published aggregate observations; result reuse terms not separately specified