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 9B; 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 9B; 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 9B; 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 9B; 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 9B; 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 9B; 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 9B; 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 9B; 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 9B; 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 9B; 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 9B; 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.1548789351294527,"accuracy":0.7837837837837838,"positive_recall":0.7464788732394366,"specificity":0.8181818181818182,"precision":0.7910447761194029,"balanced_accuracy":0.7823303457106274,"f1":0.7681159420289855,"true_positive":53,"false_positive":14,"false_negative":18,"true_negative":63,"positive_prevalence":0.4797297297297297,"majority_accuracy_baseline":0.5202702702702703,"constant_brier_baseline":0.24958911614317017,"brier_skill":0.3794643872186698,"baseline_adjusted_skill":0.5646606914212549,"baseline_adjusted_score":0.5646606914212549}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.2005,"fixed_answer_accuracy_baseline":0.29,"baseline_adjusted_skill":0.4929577464788733,"baseline_adjusted_score":0.4929577464788733}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.2533333333333333,"fixed_answer_accuracy_baseline":0.32,"baseline_adjusted_skill":0.9558823529411764,"baseline_adjusted_score":0.9558823529411764}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.53,"baseline_adjusted_skill":0.7234042553191489,"baseline_adjusted_score":0.7234042553191489}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.51,"baseline_adjusted_skill":0.8775510204081631,"baseline_adjusted_score":0.8775510204081631}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.18083427801342478,"accuracy":0.53245239122,"positive_recall":0.47764115952785324,"specificity":0.6203913557716567,"precision":0.6687344571363636,"balanced_accuracy":0.549016257649755,"f1":0.5572608085512021,"true_positive":29.424316114,"false_positive":14.575683886,"false_negative":32.179076992,"true_negative":23.820923008,"positive_prevalence":0.61603393106,"majority_accuracy_baseline":0.61603393106,"constant_brier_baseline":0.07908707655202402,"brier_skill":-1.2865212105099215,"baseline_adjusted_skill":0.09803251529951007,"baseline_adjusted_score":0.09803251529951007}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.12560579286412,"accuracy":0.82,"positive_recall":0.8,"specificity":0.84,"precision":0.8333333333333334,"balanced_accuracy":0.8200000000000001,"f1":0.8163265306122449,"true_positive":40,"false_positive":8,"false_negative":10,"true_negative":42,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.49757682854352003,"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/banking77 / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.012987012987012986,"fixed_answer_accuracy_baseline":0.05,"baseline_adjusted_skill":0.8947368421052632,"baseline_adjusted_score":0.8947368421052632}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.96,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.4,"baseline_adjusted_skill":0.9333333333333332,"baseline_adjusted_score":0.9333333333333332}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.33333333333333326,"fixed_answer_accuracy_baseline":0.36,"baseline_adjusted_skill":0.25000000000000006,"baseline_adjusted_score":0.25000000000000006}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.11336155400515001,"accuracy":0.83,"positive_recall":1,"specificity":0.66,"precision":0.746268656716418,"balanced_accuracy":0.8300000000000001,"f1":0.8547008547008547,"true_positive":50,"false_positive":17,"false_negative":0,"true_negative":33,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.5465537839793999,"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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.075115740877932,"accuracy":0.7078718392198373,"positive_recall":0.6270511504124998,"specificity":0.7455049190114259,"precision":0.534295332871406,"balanced_accuracy":0.6862780347119628,"f1":0.5769690750510367,"true_positive":139.45108187943697,"false_positive":121.54891812056303,"false_negative":82.94079442555085,"true_negative":356.05920557444915,"positive_prevalence":0.3177026804356969,"majority_accuracy_baseline":0.6822973195643032,"constant_brier_baseline":0.08872692397768642,"brier_skill":0.1534053305305325,"baseline_adjusted_skill":0.3725560694239256,"baseline_adjusted_score":0.3725560694239256}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.06607604224171,"accuracy":0.91,"positive_recall":0.88,"specificity":0.94,"precision":0.9361702127659575,"balanced_accuracy":0.9099999999999999,"f1":0.9072164948453608,"true_positive":44,"false_positive":3,"false_negative":6,"true_negative":47,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.73569583103316,"baseline_adjusted_skill":0.8199999999999998,"baseline_adjusted_score":0.8199999999999998}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.9602649006622517,"uniform_accuracy_baseline":0.006622516556291391,"fixed_answer_accuracy_baseline":0.039735099337748346,"baseline_adjusted_skill":0.9586206896551724,"baseline_adjusted_score":0.9586206896551724}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.09824280494064333,"accuracy":0.8666666666666667,"positive_recall":0.7533333333333333,"specificity":0.98,"precision":0.9741379310344828,"balanced_accuracy":0.8666666666666667,"f1":0.849624060150376,"true_positive":113,"false_positive":3,"false_negative":37,"true_negative":147,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.6070287802374267,"baseline_adjusted_skill":0.7333333333333334,"baseline_adjusted_score":0.7333333333333334}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.8870588235294118,"uniform_accuracy_baseline":0.3333333333333333,"fixed_answer_accuracy_baseline":0.4576470588235294,"baseline_adjusted_skill":0.7917570498915402,"baseline_adjusted_score":0.7917570498915402}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.33333333333333326,"fixed_answer_accuracy_baseline":0.4,"baseline_adjusted_skill":0.08333333333333331,"baseline_adjusted_score":0.08333333333333331}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.09672366970021001,"accuracy":0.87,"positive_recall":0.96,"specificity":0.78,"precision":0.8135593220338984,"balanced_accuracy":0.87,"f1":0.8807339449541285,"true_positive":48,"false_positive":11,"false_negative":2,"true_negative":39,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.61310532119916,"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/crows_pairs / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.5,"fixed_answer_accuracy_baseline":0.52,"baseline_adjusted_skill":0.5,"baseline_adjusted_score":0.5}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.9266666666666666,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.5,"baseline_adjusted_skill":0.8533333333333333,"baseline_adjusted_score":0.8533333333333333}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.7266666666666667,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.52,"baseline_adjusted_skill":0.4305555555555556,"baseline_adjusted_score":0.4305555555555556}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.9266666666666666,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.5266666666666666,"baseline_adjusted_skill":0.8450704225352113,"baseline_adjusted_score":0.8450704225352113}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.07142857142857142,"fixed_answer_accuracy_baseline":0.11,"baseline_adjusted_skill":0.9887640449438202,"baseline_adjusted_score":0.9887640449438202}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.5,"fixed_answer_accuracy_baseline":0.54,"baseline_adjusted_skill":0.7608695652173914,"baseline_adjusted_score":0.7608695652173914}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.27,"baseline_adjusted_skill":0.2465753424657534,"baseline_adjusted_score":0.2465753424657534}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.5,"fixed_answer_accuracy_baseline":0.6666666666666666,"baseline_adjusted_skill":0.3333333333333334,"baseline_adjusted_score":0.3333333333333334}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.19536707638791462,"accuracy":0.6951219512195121,"positive_recall":0.625,"specificity":0.7619047619047619,"precision":0.7142857142857143,"balanced_accuracy":0.6934523809523809,"f1":0.6666666666666666,"true_positive":25,"false_positive":10,"false_negative":15,"true_negative":32,"positive_prevalence":0.4878048780487805,"majority_accuracy_baseline":0.5121951219512195,"constant_brier_baseline":0.2498512790005949,"brier_skill":0.21806653474265603,"baseline_adjusted_skill":0.38690476190476186,"baseline_adjusted_score":0.38690476190476186}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.15143655801498,"accuracy":0.77,"positive_recall":0.7,"specificity":0.84,"precision":0.813953488372093,"balanced_accuracy":0.77,"f1":0.7526881720430108,"true_positive":35,"false_positive":8,"false_negative":15,"true_negative":42,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.39425376794008005,"baseline_adjusted_skill":0.54,"baseline_adjusted_score":0.54}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.7430167597765364,"uniform_accuracy_baseline":0.125,"fixed_answer_accuracy_baseline":0.2206703910614525,"baseline_adjusted_skill":0.6702508960573478,"baseline_adjusted_score":0.6702508960573478}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.33333333333333326,"fixed_answer_accuracy_baseline":0.39,"baseline_adjusted_skill":0.21311475409836067,"baseline_adjusted_score":0.21311475409836067}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.155540198886675,"accuracy":0.785,"positive_recall":0.38636363636363635,"specificity":0.8974358974358975,"precision":0.5151515151515151,"balanced_accuracy":0.6418997668997669,"f1":0.44155844155844154,"true_positive":17,"false_positive":16,"false_negative":27,"true_negative":140,"positive_prevalence":0.22,"majority_accuracy_baseline":0.78,"constant_brier_baseline":0.1716,"brier_skill":0.093588584576486,"baseline_adjusted_skill":0.2837995337995338,"baseline_adjusted_score":0.2837995337995338}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.18878756090394,"accuracy":0.75,"positive_recall":0.04,"specificity":0.9866666666666667,"precision":0.5,"balanced_accuracy":0.5133333333333333,"f1":0.07407407407407407,"true_positive":2,"false_positive":2,"false_negative":48,"true_negative":148,"positive_prevalence":0.25,"majority_accuracy_baseline":0.75,"constant_brier_baseline":0.1875,"brier_skill":-0.0068669914876799965,"baseline_adjusted_skill":0.026666666666666616,"baseline_adjusted_score":0.026666666666666616}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.028553038530850002,"accuracy":0.955,"positive_recall":0.5789473684210527,"specificity":0.994475138121547,"precision":0.9166666666666666,"balanced_accuracy":0.7867112532712999,"f1":0.7096774193548387,"true_positive":11,"false_positive":1,"false_negative":8,"true_negative":180,"positive_prevalence":0.095,"majority_accuracy_baseline":0.905,"constant_brier_baseline":0.085975,"brier_skill":0.6678913808566443,"baseline_adjusted_skill":0.5734225065425997,"baseline_adjusted_score":0.5734225065425997}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.9966666666666667,"uniform_accuracy_baseline":0.3333333333333333,"fixed_answer_accuracy_baseline":0.3333333333333333,"baseline_adjusted_skill":0.9949999999999999,"baseline_adjusted_score":0.9949999999999999}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.01909394610629,"accuracy":0.9833333333333333,"positive_recall":0.9866666666666667,"specificity":0.98,"precision":0.9801324503311258,"balanced_accuracy":0.9833333333333334,"f1":0.9833887043189369,"true_positive":148,"false_positive":3,"false_negative":2,"true_negative":147,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.92362421557484,"baseline_adjusted_skill":0.9666666666666668,"baseline_adjusted_score":0.9666666666666668}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.9644444444444445,"baseline_adjusted_score":0.9644444444444445}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.14561735241087667,"accuracy":0.7866666666666666,"positive_recall":0.9866666666666667,"specificity":0.5866666666666667,"precision":0.7047619047619048,"balanced_accuracy":0.7866666666666666,"f1":0.8222222222222222,"true_positive":148,"false_positive":62,"false_negative":2,"true_negative":88,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.4175305903564933,"baseline_adjusted_skill":0.5733333333333333,"baseline_adjusted_score":0.5733333333333333}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.15925890799495934,"normalized_score_rmse":0.21450400850054713,"constant_score_baseline":0.5,"constant_mae_baseline":0.3333333333333333,"baseline_adjusted_skill":0.522223276015122,"baseline_adjusted_score":0.522223276015122}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.33666666666666667,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.11555555555555556,"baseline_adjusted_score":0.11555555555555556}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.24782380112382,"accuracy":0.54,"positive_recall":0.5733333333333334,"specificity":0.5066666666666667,"precision":0.5375,"balanced_accuracy":0.54,"f1":0.5548387096774193,"true_positive":86,"false_positive":74,"false_negative":64,"true_negative":76,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.008704795504720031,"baseline_adjusted_skill":0.08000000000000007,"baseline_adjusted_score":0.08000000000000007}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.2969772298679768,"normalized_score_rmse":0.34446157695021434,"constant_score_baseline":0.5,"constant_mae_baseline":0.3,"baseline_adjusted_skill":0.010075900440077223,"baseline_adjusted_score":0.010075900440077223}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.9466666666666667,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.3,"baseline_adjusted_skill":0.923809523809524,"baseline_adjusted_score":0.923809523809524}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.01873097499922,"accuracy":0.9833333333333333,"positive_recall":0.9798657718120806,"specificity":0.9867549668874173,"precision":0.9864864864864865,"balanced_accuracy":0.9833103693497489,"f1":0.9831649831649831,"true_positive":146,"false_positive":2,"false_negative":3,"true_negative":149,"positive_prevalence":0.49666666666666665,"majority_accuracy_baseline":0.5033333333333334,"constant_brier_baseline":0.2499888888888889,"brier_skill":0.9250727699040047,"baseline_adjusted_skill":0.9666207386994978,"baseline_adjusted_score":0.9666207386994978}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.1804184817082045,"normalized_score_rmse":0.23530479989249722,"constant_score_baseline":0.5,"constant_mae_baseline":0.36666666666666664,"baseline_adjusted_skill":0.5079495953412605,"baseline_adjusted_score":0.5079495953412605}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.7,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.2866666666666667,"baseline_adjusted_skill":0.5794392523364484,"baseline_adjusted_score":0.5794392523364484}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.15035502882583665,"accuracy":0.79,"positive_recall":0.8343949044585988,"specificity":0.7412587412587412,"precision":0.7797619047619048,"balanced_accuracy":0.78782682285867,"f1":0.8061538461538461,"true_positive":131,"false_positive":37,"false_negative":26,"true_negative":106,"positive_prevalence":0.5233333333333333,"majority_accuracy_baseline":0.5233333333333333,"constant_brier_baseline":0.24945555555555557,"brier_skill":0.39726726674422974,"baseline_adjusted_skill":0.57565364571734,"baseline_adjusted_score":0.57565364571734}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.248882113641003,"normalized_score_rmse":0.30699199686947104,"constant_score_baseline":0.5,"constant_mae_baseline":0.3016666666666667,"baseline_adjusted_skill":0.17497641886960347,"baseline_adjusted_score":0.17497641886960347}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.06359842898474317,"accuracy":0.879267857142857,"positive_recall":0.5355619482194227,"specificity":0.9012088475737561,"precision":0.2570952380952381,"balanced_accuracy":0.7183853978965894,"f1":0.347414819343007,"true_positive":89.98333333333333,"false_positive":260.01666666666665,"false_negative":78.03333333333333,"true_negative":2371.9666666666667,"positive_prevalence":0.060005952380952375,"majority_accuracy_baseline":0.9399940476190476,"constant_brier_baseline":0.03220097218679138,"brier_skill":-0.975046859325285,"baseline_adjusted_skill":0.4367707957931788,"baseline_adjusted_score":0.4367707957931788}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.44333333333333336,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.25777777777777783,"baseline_adjusted_score":0.25777777777777783}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.7337110481586402,"uniform_accuracy_baseline":0.027777777777777776,"fixed_answer_accuracy_baseline":0.1274787535410765,"baseline_adjusted_skill":0.6948051948051948,"baseline_adjusted_score":0.6948051948051948}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.84,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.3,"baseline_adjusted_skill":0.7714285714285716,"baseline_adjusted_score":0.7714285714285716}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.11782001431842,"accuracy":0.83,"positive_recall":1,"specificity":0.66,"precision":0.746268656716418,"balanced_accuracy":0.8300000000000001,"f1":0.8547008547008547,"true_positive":50,"false_positive":17,"false_negative":0,"true_negative":33,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.5287199427263201,"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/hatecheck / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.07712789445164,"accuracy":0.89,"positive_recall":0.98,"specificity":0.8,"precision":0.8305084745762712,"balanced_accuracy":0.89,"f1":0.8990825688073395,"true_positive":49,"false_positive":10,"false_negative":1,"true_negative":40,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.69148842219344,"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/hh_rlhf / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.5,"fixed_answer_accuracy_baseline":0.61,"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/hwu64 / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.015625,"fixed_answer_accuracy_baseline":0.06,"baseline_adjusted_skill":0.8510638297872342,"baseline_adjusted_score":0.8510638297872342}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.08808634322586001,"accuracy":0.88,"positive_recall":0.92,"specificity":0.84,"precision":0.8518518518518519,"balanced_accuracy":0.88,"f1":0.8846153846153846,"true_positive":46,"false_positive":8,"false_negative":4,"true_negative":42,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.64765462709656,"baseline_adjusted_skill":0.76,"baseline_adjusted_score":0.76}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.25333333333333335,"baseline_adjusted_score":0.25333333333333335}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.6866666666666666,"uniform_accuracy_baseline":0.3333333333333333,"fixed_answer_accuracy_baseline":0.3333333333333333,"baseline_adjusted_skill":0.5299999999999999,"baseline_adjusted_score":0.5299999999999999}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.6947368421052632,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.5263157894736842,"baseline_adjusted_skill":0.3555555555555557,"baseline_adjusted_score":0.3555555555555557}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.26259148164322405,"accuracy":0.5652173913043478,"positive_recall":0.9533333333333334,"specificity":0.174496644295302,"precision":0.5375939849624061,"balanced_accuracy":0.5639149888143177,"f1":0.6875,"true_positive":143,"false_positive":123,"false_negative":7,"true_negative":26,"positive_prevalence":0.5016722408026756,"majority_accuracy_baseline":0.5016722408026756,"constant_brier_baseline":0.24999720361069788,"brier_skill":-0.050377675632477414,"baseline_adjusted_skill":0.12782997762863535,"baseline_adjusted_score":0.12782997762863535}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.9566666666666667,"uniform_accuracy_baseline":0.2,"fixed_answer_accuracy_baseline":0.2,"baseline_adjusted_skill":0.9458333333333332,"baseline_adjusted_score":0.9458333333333332}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.3146014232878021,"accuracy":0.5512367491166078,"positive_recall":0.8571428571428571,"specificity":0.28,"precision":0.5135135135135135,"balanced_accuracy":0.5685714285714285,"f1":0.6422535211267606,"true_positive":114,"false_positive":108,"false_negative":19,"true_negative":42,"positive_prevalence":0.46996466431095407,"majority_accuracy_baseline":0.5300353356890459,"constant_brier_baseline":0.24909787861004634,"brier_skill":-0.26296307717778356,"baseline_adjusted_skill":0.137142857142857,"baseline_adjusted_score":0.137142857142857}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.8166666666666667,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.7555555555555555,"baseline_adjusted_score":0.7555555555555555}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.20616666666666666,"fixed_answer_accuracy_baseline":0.21333333333333335,"baseline_adjusted_skill":0.9661016949152543,"baseline_adjusted_score":0.9661016949152543}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.3333333333333333,"fixed_answer_accuracy_baseline":0.3333333333333333,"baseline_adjusted_skill":0.74,"baseline_adjusted_score":0.74}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.7366666666666667,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.37333333333333335,"baseline_adjusted_skill":0.5797872340425532,"baseline_adjusted_score":0.5797872340425532}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.12307515711386535,"normalized_score_rmse":0.15090949760701416,"constant_score_baseline":0.5,"constant_mae_baseline":0.26208333333333333,"baseline_adjusted_skill":0.5303968567992419,"baseline_adjusted_score":0.5303968567992419}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.12617575837826128,"normalized_score_rmse":0.1620104287204834,"constant_score_baseline":0.52,"constant_mae_baseline":0.24733333333333335,"baseline_adjusted_skill":0.4898554243466525,"baseline_adjusted_score":0.4898554243466525}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.15042385318598245,"normalized_score_rmse":0.1701898206955265,"constant_score_baseline":0.578319964349225,"constant_mae_baseline":0.11212962028602311,"baseline_adjusted_skill":-0.34151754730175155,"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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.7766666666666666,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.7022222222222222,"baseline_adjusted_score":0.7022222222222222}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.25,"fixed_answer_accuracy_baseline":0.33,"baseline_adjusted_skill":0.8507462686567167,"baseline_adjusted_score":0.8507462686567167}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.06090997866032,"accuracy":0.92,"positive_recall":0.86,"specificity":0.98,"precision":0.9772727272727273,"balanced_accuracy":0.9199999999999999,"f1":0.9148936170212766,"true_positive":43,"false_positive":1,"false_negative":7,"true_negative":49,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.75636008535872,"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/laya__typed_decisions / test · target_mass_at_prediction. Population 100 cases / 148 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.4853976148648649,"uniform_accuracy_baseline":0.23445945945945948,"fixed_answer_accuracy_baseline":0.2623439054054054,"baseline_adjusted_skill":0.302381707538181,"baseline_adjusted_score":0.302381707538181}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.05058841415036842,"accuracy":0.6883771513157896,"positive_recall":0.7403110706645102,"specificity":0.6389245301409401,"precision":0.6612851204819277,"balanced_accuracy":0.6896178004027251,"f1":0.6985702424862498,"true_positive":54.886665,"false_positive":28.113335,"false_negative":19.253338,"true_negative":49.746662,"positive_prevalence":0.4877631776315789,"majority_accuracy_baseline":0.512236822368421,"constant_brier_baseline":0.09451910039768556,"brier_skill":0.4647810449155825,"baseline_adjusted_skill":0.37923560080545027,"baseline_adjusted_score":0.37923560080545027}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.11678694493008111,"normalized_score_rmse":0.16314800208691715,"constant_score_baseline":0.5841668333333333,"constant_mae_baseline":0.21700552708333334,"baseline_adjusted_skill":0.46182502123444447,"baseline_adjusted_score":0.46182502123444447}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.22670658587956002,"accuracy":0.69,"positive_recall":0.94,"specificity":0.44,"precision":0.6266666666666667,"balanced_accuracy":0.69,"f1":0.752,"true_positive":47,"false_positive":28,"false_negative":3,"true_negative":22,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.0931736564817599,"baseline_adjusted_skill":0.3799999999999999,"baseline_adjusted_score":0.3799999999999999}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.29124831159907,"accuracy":0.61,"positive_recall":0.24,"specificity":0.98,"precision":0.9230769230769231,"balanced_accuracy":0.61,"f1":0.38095238095238093,"true_positive":12,"false_positive":1,"false_negative":38,"true_negative":49,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.16499324639628,"baseline_adjusted_skill":0.21999999999999997,"baseline_adjusted_score":0.21999999999999997}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.33333333333333326,"fixed_answer_accuracy_baseline":0.39,"baseline_adjusted_skill":0.819672131147541,"baseline_adjusted_score":0.819672131147541}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.036111111111111115,"fixed_answer_accuracy_baseline":0.08833333333333333,"baseline_adjusted_skill":0.9012797074954296,"baseline_adjusted_score":0.9012797074954296}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.1840943437759,"accuracy":0.7166666666666667,"positive_recall":0.8266666666666667,"specificity":0.6066666666666667,"precision":0.6775956284153005,"balanced_accuracy":0.7166666666666667,"f1":0.7447447447447447,"true_positive":124,"false_positive":59,"false_negative":26,"true_negative":91,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.2636226248964,"baseline_adjusted_skill":0.43333333333333335,"baseline_adjusted_score":0.43333333333333335}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.11021428571428572,"fixed_answer_accuracy_baseline":0.12554761904761905,"baseline_adjusted_skill":0.47395648977591426,"baseline_adjusted_score":0.47395648977591426}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.6933333333333334,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.25,"baseline_adjusted_skill":0.5911111111111111,"baseline_adjusted_score":0.5911111111111111}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.18772566367584334,"accuracy":0.6966666666666667,"positive_recall":0.6018518518518519,"specificity":0.9404761904761905,"precision":0.9629629629629629,"balanced_accuracy":0.7711640211640212,"f1":0.7407407407407407,"true_positive":130,"false_positive":5,"false_negative":86,"true_negative":79,"positive_prevalence":0.72,"majority_accuracy_baseline":0.72,"constant_brier_baseline":0.2016,"brier_skill":0.06882111271903102,"baseline_adjusted_skill":0.5423280423280423,"baseline_adjusted_score":0.5423280423280423}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.9233333333333333,"uniform_accuracy_baseline":0.5,"fixed_answer_accuracy_baseline":0.5033333333333333,"baseline_adjusted_skill":0.8456375838926175,"baseline_adjusted_score":0.8456375838926175}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.27034718575876,"accuracy":0.52,"positive_recall":0.1,"specificity":0.94,"precision":0.625,"balanced_accuracy":0.52,"f1":0.1724137931034483,"true_positive":5,"false_positive":3,"false_negative":45,"true_negative":47,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.08138874303503996,"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/nlvr2-noul / test · binary_brier. Population 300 cases / 300 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.43951085594393996,"accuracy":0.5366666666666666,"positive_recall":1,"specificity":0.007142857142857143,"precision":0.5351170568561873,"balanced_accuracy":0.5035714285714286,"f1":0.6971677559912854,"true_positive":160,"false_positive":139,"false_negative":0,"true_negative":1,"positive_prevalence":0.5333333333333333,"majority_accuracy_baseline":0.5333333333333333,"constant_brier_baseline":0.2488888888888889,"brier_skill":-0.7658918319176158,"baseline_adjusted_skill":0.0071428571428571175,"baseline_adjusted_score":0.0071428571428571175}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.1296060703051875,"accuracy":0.8125,"positive_recall":0.90625,"specificity":0.71875,"precision":0.7631578947368421,"balanced_accuracy":0.8125,"f1":0.8285714285714286,"true_positive":29,"false_positive":9,"false_negative":3,"true_negative":23,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.48157571877925,"baseline_adjusted_skill":0.625,"baseline_adjusted_score":0.625}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.83,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.34,"baseline_adjusted_skill":0.7424242424242424,"baseline_adjusted_score":0.7424242424242424}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.34487416730981,"accuracy":0.52,"positive_recall":0.1,"specificity":0.94,"precision":0.625,"balanced_accuracy":0.52,"f1":0.1724137931034483,"true_positive":5,"false_positive":3,"false_negative":45,"true_negative":47,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.3794966692392401,"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/open_jev__customer-control-v1 / test · target_mass_at_prediction. Population 17 cases / 17 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.7941176470588235,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.3235294117647059,"baseline_adjusted_skill":0.6956521739130433,"baseline_adjusted_score":0.6956521739130433}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.13787681955533335,"accuracy":0.8787878787878788,"positive_recall":1,"specificity":0.7647058823529411,"precision":0.8,"balanced_accuracy":0.8823529411764706,"f1":0.8888888888888888,"true_positive":16,"false_positive":4,"false_negative":0,"true_negative":13,"positive_prevalence":0.48484848484848486,"majority_accuracy_baseline":0.5151515151515151,"constant_brier_baseline":0.2497704315886134,"brier_skill":0.44798582170677204,"baseline_adjusted_skill":0.7647058823529411,"baseline_adjusted_score":0.7647058823529411}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.15957199935981706,"normalized_score_rmse":0.2821104544239652,"constant_score_baseline":0.25,"constant_mae_baseline":0.33,"baseline_adjusted_skill":0.5164484867884331,"baseline_adjusted_score":0.5164484867884331}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.4375,"uniform_accuracy_baseline":0.178125,"fixed_answer_accuracy_baseline":0.2875,"baseline_adjusted_skill":0.2105263157894737,"baseline_adjusted_score":0.2105263157894737}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.3031853806481471,"accuracy":0.5,"positive_recall":0,"specificity":1,"precision":null,"balanced_accuracy":0.5,"f1":0,"true_positive":0,"false_positive":0,"false_negative":17,"true_negative":17,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.21274152259258838,"baseline_adjusted_skill":0,"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__drone-control-v1 / test · normalized_expected_score_mae. Population 34 cases / 34 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.19709634809561447,"normalized_score_rmse":0.2449629863541562,"constant_score_baseline":0.5,"constant_mae_baseline":0.14705882352941177,"baseline_adjusted_skill":-0.34025516705017833,"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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.5416666666666666,"uniform_accuracy_baseline":0.13194444444444445,"fixed_answer_accuracy_baseline":0.6006944444444444,"baseline_adjusted_skill":-0.14782608695652177,"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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.13777286589888463,"accuracy":0.8653846153846154,"positive_recall":1,"specificity":0.7307692307692307,"precision":0.7878787878787878,"balanced_accuracy":0.8653846153846154,"f1":0.8813559322033898,"true_positive":26,"false_positive":7,"false_negative":0,"true_negative":19,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.4489085364044615,"baseline_adjusted_skill":0.7307692307692308,"baseline_adjusted_score":0.7307692307692308}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.09409264865949334,"accuracy":0.84,"positive_recall":1,"specificity":0.6666666666666666,"precision":0.7647058823529411,"balanced_accuracy":0.8333333333333333,"f1":0.8666666666666667,"true_positive":39,"false_positive":12,"false_negative":0,"true_negative":24,"positive_prevalence":0.52,"majority_accuracy_baseline":0.52,"constant_brier_baseline":0.24960000000000004,"brier_skill":0.6230262473577992,"baseline_adjusted_skill":0.6666666666666665,"baseline_adjusted_score":0.6666666666666665}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.2546262403480907,"normalized_score_rmse":0.31274530569260767,"constant_score_baseline":0.5,"constant_mae_baseline":0.28,"baseline_adjusted_skill":0.09062057018539038,"baseline_adjusted_score":0.09062057018539038}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.11560656071517858,"accuracy":0.7857142857142857,"positive_recall":1,"specificity":0.5714285714285714,"precision":0.7,"balanced_accuracy":0.7857142857142857,"f1":0.8235294117647058,"true_positive":14,"false_positive":6,"false_negative":0,"true_negative":8,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.5375737571392857,"baseline_adjusted_skill":0.5714285714285714,"baseline_adjusted_score":0.5714285714285714}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.2015277164322653,"normalized_score_rmse":0.29284634201131093,"constant_score_baseline":0.3333333333333333,"constant_mae_baseline":0.1696969696969697,"baseline_adjusted_skill":-0.18757404326156335,"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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.06834249195503529,"accuracy":0.9058823529411765,"positive_recall":1,"specificity":0.8,"precision":0.8490566037735849,"balanced_accuracy":0.9,"f1":0.9183673469387755,"true_positive":45,"false_positive":8,"false_negative":0,"true_negative":32,"positive_prevalence":0.5294117647058824,"majority_accuracy_baseline":0.5294117647058824,"constant_brier_baseline":0.2491349480968858,"brier_skill":0.7256808309027056,"baseline_adjusted_skill":0.8,"baseline_adjusted_score":0.8}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.07805555555555556,"fixed_answer_accuracy_baseline":0.24,"baseline_adjusted_skill":1,"baseline_adjusted_score":1}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.28105367409554005,"accuracy":0.7,"positive_recall":0.5714285714285714,"specificity":1,"precision":1,"balanced_accuracy":0.7857142857142857,"f1":0.7272727272727273,"true_positive":20,"false_positive":0,"false_negative":15,"true_negative":15,"positive_prevalence":0.7,"majority_accuracy_baseline":0.7,"constant_brier_baseline":0.21,"brier_skill":-0.33835082902638125,"baseline_adjusted_skill":0.5714285714285714,"baseline_adjusted_score":0.5714285714285714}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.19328713810731737,"normalized_score_rmse":0.3343114569988732,"constant_score_baseline":0.5,"constant_mae_baseline":0.28,"baseline_adjusted_skill":0.3096887924738666,"baseline_adjusted_score":0.3096887924738666}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.8734177215189873,"uniform_accuracy_baseline":0.24240506329113923,"fixed_answer_accuracy_baseline":0.4177215189873418,"baseline_adjusted_skill":0.782608695652174,"baseline_adjusted_score":0.782608695652174}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.004748060928142857,"accuracy":1,"positive_recall":1,"specificity":1,"precision":1,"balanced_accuracy":1,"f1":1,"true_positive":11,"false_positive":0,"false_negative":0,"true_negative":10,"positive_prevalence":0.5238095238095238,"majority_accuracy_baseline":0.5238095238095238,"constant_brier_baseline":0.2494331065759637,"brier_skill":0.9809645920971727,"baseline_adjusted_skill":1,"baseline_adjusted_score":1}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.18324496934039394,"accuracy":0.7575757575757576,"positive_recall":0.6470588235294118,"specificity":0.875,"precision":0.8461538461538461,"balanced_accuracy":0.7610294117647058,"f1":0.7333333333333333,"true_positive":11,"false_positive":2,"false_negative":6,"true_negative":14,"positive_prevalence":0.5151515151515151,"majority_accuracy_baseline":0.5151515151515151,"constant_brier_baseline":0.2497704315886134,"brier_skill":0.2663464278982022,"baseline_adjusted_skill":0.5220588235294117,"baseline_adjusted_score":0.5220588235294117}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.19578465010706575,"normalized_score_rmse":0.27675832622512136,"constant_score_baseline":0.7083333333333333,"constant_mae_baseline":0.3431372549019608,"baseline_adjusted_skill":0.42942759111655127,"baseline_adjusted_score":0.42942759111655127}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.36055573010096,"accuracy":0.39,"positive_recall":0.54,"specificity":0.24,"precision":0.4153846153846154,"balanced_accuracy":0.39,"f1":0.46956521739130436,"true_positive":27,"false_positive":38,"false_negative":23,"true_negative":12,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.4422229204038399,"baseline_adjusted_skill":-0.21999999999999997,"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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.33333333333333326,"fixed_answer_accuracy_baseline":0.35333333333333333,"baseline_adjusted_skill":0.09278350515463916,"baseline_adjusted_score":0.09278350515463916}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.22770742109005335,"accuracy":0.5866666666666667,"positive_recall":0.40540540540540543,"specificity":0.7631578947368421,"precision":0.625,"balanced_accuracy":0.5842816500711238,"f1":0.4918032786885246,"true_positive":15,"false_positive":9,"false_negative":22,"true_negative":29,"positive_prevalence":0.49333333333333335,"majority_accuracy_baseline":0.5066666666666666,"constant_brier_baseline":0.24995555555555554,"brier_skill":0.08900836157073244,"baseline_adjusted_skill":0.16856330014224752,"baseline_adjusted_score":0.16856330014224752}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.14285714285714285,"fixed_answer_accuracy_baseline":0.22,"baseline_adjusted_skill":0.8205128205128205,"baseline_adjusted_score":0.8205128205128205}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.36,"uniform_accuracy_baseline":0.32416666666666666,"fixed_answer_accuracy_baseline":0.34,"baseline_adjusted_skill":0.03030303030303025,"baseline_adjusted_score":0.03030303030303025}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.28277195204269695,"accuracy":0.5151515151515151,"positive_recall":0,"specificity":1,"precision":null,"balanced_accuracy":0.5,"f1":0,"true_positive":0,"false_positive":0,"false_negative":16,"true_negative":17,"positive_prevalence":0.48484848484848486,"majority_accuracy_baseline":0.5151515151515151,"constant_brier_baseline":0.2497704315886134,"brier_skill":-0.13212741093565072,"baseline_adjusted_skill":0,"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__vizdoom-basic-v1 / test · normalized_expected_score_mae. Population 33 cases / 33 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.13324426939278197,"normalized_score_rmse":0.15521965960303544,"constant_score_baseline":0.5,"constant_mae_baseline":0.2196969696969697,"baseline_adjusted_skill":0.393508842763889,"baseline_adjusted_score":0.393508842763889}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.15310559460296,"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":0.10777625522750589,"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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.10009695807328998,"accuracy":0.91,"positive_recall":0.7837837837837838,"specificity":0.9841269841269841,"precision":0.9666666666666667,"balanced_accuracy":0.883955383955384,"f1":0.8656716417910447,"true_positive":29,"false_positive":1,"false_negative":8,"true_negative":62,"positive_prevalence":0.37,"majority_accuracy_baseline":0.63,"constant_brier_baseline":0.23310000000000003,"brier_skill":0.5705836204492065,"baseline_adjusted_skill":0.767910767910768,"baseline_adjusted_score":0.767910767910768}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.15596593975544,"accuracy":0.76,"positive_recall":0.46153846153846156,"specificity":0.9508196721311475,"precision":0.8571428571428571,"balanced_accuracy":0.7061790668348045,"f1":0.6,"true_positive":18,"false_positive":3,"false_negative":21,"true_negative":58,"positive_prevalence":0.39,"majority_accuracy_baseline":0.61,"constant_brier_baseline":0.2379,"brier_skill":0.3444054655088693,"baseline_adjusted_skill":0.41235813366960894,"baseline_adjusted_score":0.41235813366960894}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.034012791996070005,"accuracy":0.95,"positive_recall":0.8709677419354839,"specificity":0.9855072463768116,"precision":0.9642857142857143,"balanced_accuracy":0.9282374941561478,"f1":0.9152542372881356,"true_positive":27,"false_positive":1,"false_negative":4,"true_negative":68,"positive_prevalence":0.31,"majority_accuracy_baseline":0.69,"constant_brier_baseline":0.21389999999999998,"brier_skill":0.84098741469813,"baseline_adjusted_skill":0.8564749883122955,"baseline_adjusted_score":0.8564749883122955}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.25,"fixed_answer_accuracy_baseline":0.28,"baseline_adjusted_skill":0.9166666666666666,"baseline_adjusted_score":0.9166666666666666}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.17645473546190224,"normalized_score_rmse":0.22029197255703853,"constant_score_baseline":0.25,"constant_mae_baseline":0.2325,"baseline_adjusted_skill":0.2410549012391302,"baseline_adjusted_score":0.2410549012391302}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.13570934063187,"accuracy":0.81,"positive_recall":0.84,"specificity":0.78,"precision":0.7924528301886793,"balanced_accuracy":0.81,"f1":0.8155339805825242,"true_positive":42,"false_positive":11,"false_negative":8,"true_negative":39,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.45716263747251995,"baseline_adjusted_skill":0.6200000000000001,"baseline_adjusted_score":0.6200000000000001}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.30580464427730997,"accuracy":0.54,"positive_recall":0.76,"specificity":0.32,"precision":0.5277777777777778,"balanced_accuracy":0.54,"f1":0.6229508196721312,"true_positive":38,"false_positive":34,"false_negative":12,"true_negative":16,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.22321857710923987,"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/poem_sentiment / test · target_mass_at_prediction. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.59,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.65,"baseline_adjusted_skill":-0.1714285714285716,"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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.09155148499819,"accuracy":0.8733333333333333,"positive_recall":0.8133333333333334,"specificity":0.9333333333333333,"precision":0.9242424242424242,"balanced_accuracy":0.8733333333333333,"f1":0.8652482269503546,"true_positive":122,"false_positive":10,"false_negative":28,"true_negative":140,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.63379406000724,"baseline_adjusted_skill":0.7466666666666666,"baseline_adjusted_score":0.7466666666666666}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.08779294342117,"accuracy":0.86,"positive_recall":0.86,"specificity":0.86,"precision":0.86,"balanced_accuracy":0.86,"f1":0.86,"true_positive":43,"false_positive":7,"false_negative":7,"true_negative":43,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.64882822631532,"baseline_adjusted_skill":0.72,"baseline_adjusted_score":0.72}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.68,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.4,"baseline_adjusted_skill":0.46666666666666673,"baseline_adjusted_score":0.46666666666666673}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.16418205957104,"accuracy":0.75,"positive_recall":0.62,"specificity":0.88,"precision":0.8378378378378378,"balanced_accuracy":0.75,"f1":0.7126436781609196,"true_positive":31,"false_positive":6,"false_negative":19,"true_negative":44,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.34327176171583995,"baseline_adjusted_skill":0.5,"baseline_adjusted_score":0.5}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.6966666666666667,"uniform_accuracy_baseline":0.0625,"fixed_answer_accuracy_baseline":0.10666666666666667,"baseline_adjusted_skill":0.6604477611940298,"baseline_adjusted_score":0.6604477611940298}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.20851190476190473,"fixed_answer_accuracy_baseline":0.22333333333333333,"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/s1mb-generalization-contextual-noul / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.03982880171663,"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":0.84068479313348,"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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.09957466836048497,"normalized_score_rmse":0.1629672215224537,"constant_score_baseline":0.5,"constant_mae_baseline":0.3,"baseline_adjusted_skill":0.6680844387983834,"baseline_adjusted_score":0.6680844387983834}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.22851190476190475,"fixed_answer_accuracy_baseline":0.24333333333333332,"baseline_adjusted_skill":0.9339207048458149,"baseline_adjusted_score":0.9339207048458149}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.02662522138111,"accuracy":0.97,"positive_recall":0.98,"specificity":0.96,"precision":0.9607843137254902,"balanced_accuracy":0.97,"f1":0.9702970297029703,"true_positive":49,"false_positive":2,"false_negative":1,"true_negative":48,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.89349911447556,"baseline_adjusted_skill":0.94,"baseline_adjusted_score":0.94}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.08266121115790254,"normalized_score_rmse":0.15772554402933112,"constant_score_baseline":0.4222222222222222,"constant_mae_baseline":0.3042222222222222,"baseline_adjusted_skill":0.7282867419937462,"baseline_adjusted_score":0.7282867419937462}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.3467777777777778,"fixed_answer_accuracy_baseline":0.36,"baseline_adjusted_skill":0.9583333333333334,"baseline_adjusted_score":0.9583333333333334}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.07073675937224,"accuracy":0.91,"positive_recall":0.96,"specificity":0.86,"precision":0.8727272727272727,"balanced_accuracy":0.9099999999999999,"f1":0.9142857142857143,"true_positive":48,"false_positive":7,"false_negative":2,"true_negative":43,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.71705296251104,"baseline_adjusted_skill":0.8199999999999998,"baseline_adjusted_score":0.8199999999999998}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.33333333333333326,"fixed_answer_accuracy_baseline":0.5,"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/sdoh_nli / test · binary_brier. Population 100 cases / 100 decisions.

Exact OmniJev/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.06504885766511999,"accuracy":0.9,"positive_recall":0.84,"specificity":0.96,"precision":0.9545454545454546,"balanced_accuracy":0.8999999999999999,"f1":0.8936170212765957,"true_positive":42,"false_positive":2,"false_negative":8,"true_negative":48,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.7398045693395201,"baseline_adjusted_skill":0.7999999999999998,"baseline_adjusted_score":0.7999999999999998}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.38,"baseline_adjusted_skill":0.9032258064516128,"baseline_adjusted_score":0.9032258064516128}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.6266666666666667,"uniform_accuracy_baseline":0.3333333333333333,"fixed_answer_accuracy_baseline":0.3333333333333333,"baseline_adjusted_skill":0.44000000000000006,"baseline_adjusted_score":0.44000000000000006}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.47,"uniform_accuracy_baseline":0.25,"fixed_answer_accuracy_baseline":0.38,"baseline_adjusted_skill":0.1451612903225806,"baseline_adjusted_score":0.1451612903225806}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.43,"uniform_accuracy_baseline":0.1111111111111111,"fixed_answer_accuracy_baseline":0.16,"baseline_adjusted_skill":0.32142857142857145,"baseline_adjusted_score":0.32142857142857145}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.58,"baseline_adjusted_skill":0.8809523809523808,"baseline_adjusted_score":0.8809523809523808}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.06460030160810999,"accuracy":0.7921250000000001,"positive_recall":0.24192485168094927,"specificity":0.9208699676075891,"precision":0.41704545454545455,"balanced_accuracy":0.5813974096442692,"f1":0.3062161034626617,"true_positive":18.35,"false_positive":25.65,"false_negative":57.5,"true_negative":298.5,"positive_prevalence":0.189625,"majority_accuracy_baseline":0.8103750000000001,"constant_brier_baseline":0.07612360937500001,"brier_skill":0.15137626633182777,"baseline_adjusted_skill":0.16279481928853845,"baseline_adjusted_score":0.16279481928853845}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.18247607688933765,"normalized_score_rmse":0.21578325188459915,"constant_score_baseline":0,"constant_mae_baseline":0.21375,"baseline_adjusted_skill":0.14631075139491156,"baseline_adjusted_score":0.14631075139491156}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.0670993381288,"accuracy":0.7951250000000001,"positive_recall":0.4955461790904829,"specificity":0.9040395432077724,"precision":0.6524691358024691,"balanced_accuracy":0.6997928611491276,"f1":0.5632827071675993,"true_positive":52.85,"false_positive":28.15,"false_negative":53.8,"true_negative":265.2,"positive_prevalence":0.266625,"majority_accuracy_baseline":0.733375,"constant_brier_baseline":0.115654859375,"brier_skill":0.41983122463331424,"baseline_adjusted_skill":0.3995857222982553,"baseline_adjusted_score":0.3995857222982553}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.18371723124041445,"normalized_score_rmse":0.23138115998736142,"constant_score_baseline":0.25,"constant_mae_baseline":0.26875,"baseline_adjusted_skill":0.3164010000356672,"baseline_adjusted_score":0.3164010000356672}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.05395333179012,"accuracy":0.794875,"positive_recall":0.5713646532438479,"specificity":0.8815264527320035,"precision":0.6515306122448979,"balanced_accuracy":0.7264455529879257,"f1":0.6088200238379022,"true_positive":63.85,"false_positive":34.15,"false_negative":47.9,"true_negative":254.1,"positive_prevalence":0.279375,"majority_accuracy_baseline":0.7206250000000001,"constant_brier_baseline":0.11315585937500001,"brier_skill":0.5231945381518606,"baseline_adjusted_skill":0.45289110597585136,"baseline_adjusted_score":0.45289110597585136}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.17543148212748963,"normalized_score_rmse":0.2200093204244642,"constant_score_baseline":0.25,"constant_mae_baseline":0.264375,"baseline_adjusted_skill":0.33642938202368,"baseline_adjusted_score":0.33642938202368}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.0736186078124875,"accuracy":0.835875,"positive_recall":0.3216901408450704,"specificity":0.9824899598393575,"precision":0.8397058823529412,"balanced_accuracy":0.652090050342214,"f1":0.46517311608961304,"true_positive":28.55,"false_positive":5.45,"false_negative":60.2,"true_negative":305.8,"positive_prevalence":0.221875,"majority_accuracy_baseline":0.778125,"constant_brier_baseline":0.12674023437499998,"brier_skill":0.4191378280502134,"baseline_adjusted_skill":0.304180100684428,"baseline_adjusted_score":0.304180100684428}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.1620089319316148,"normalized_score_rmse":0.22117067139393218,"constant_score_baseline":0,"constant_mae_baseline":0.225625,"baseline_adjusted_skill":0.28195487232525296,"baseline_adjusted_score":0.28195487232525296}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.0380341969298675,"accuracy":0.8334999999999999,"positive_recall":0.7003780718336483,"specificity":0.8813732154996602,"precision":0.6798165137614678,"balanced_accuracy":0.7908756436666542,"f1":0.6899441340782123,"true_positive":74.1,"false_positive":34.9,"false_negative":31.7,"true_negative":259.3,"positive_prevalence":0.2645,"majority_accuracy_baseline":0.7355,"constant_brier_baseline":0.11362725,"brier_skill":0.6652722218493583,"baseline_adjusted_skill":0.5817512873333084,"baseline_adjusted_score":0.5817512873333084}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.16218834394998716,"normalized_score_rmse":0.2080917570963024,"constant_score_baseline":0.25,"constant_mae_baseline":0.25125,"baseline_adjusted_skill":0.3544742529353744,"baseline_adjusted_score":0.3544742529353744}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.056691674740572504,"accuracy":0.8325,"positive_recall":0.47389033942558745,"specificity":0.9174397031539889,"precision":0.5761904761904761,"balanced_accuracy":0.6956650212897881,"f1":0.5200573065902578,"true_positive":36.3,"false_positive":26.7,"false_negative":40.3,"true_negative":296.7,"positive_prevalence":0.19149999999999998,"majority_accuracy_baseline":0.8085,"constant_brier_baseline":0.09190274999999999,"brier_skill":0.3831340766128053,"baseline_adjusted_skill":0.39133004257957626,"baseline_adjusted_score":0.39133004257957626}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.1667112146284494,"normalized_score_rmse":0.21571368991024492,"constant_score_baseline":0,"constant_mae_baseline":0.206875,"baseline_adjusted_skill":0.19414518608604525,"baseline_adjusted_score":0.19414518608604525}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.03661670229621,"accuracy":0.897,"positive_recall":0.6409214092140921,"specificity":0.9549356223175967,"precision":0.7629032258064515,"balanced_accuracy":0.7979285157658444,"f1":0.6966126656848305,"true_positive":47.3,"false_positive":14.7,"false_negative":26.5,"true_negative":311.5,"positive_prevalence":0.1845,"majority_accuracy_baseline":0.8155,"constant_brier_baseline":0.10922225,"brier_skill":0.6647505220208336,"baseline_adjusted_skill":0.5958570315316889,"baseline_adjusted_score":0.5958570315316889}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.15738589774582012,"normalized_score_rmse":0.21005454993937464,"constant_score_baseline":0,"constant_mae_baseline":0.189375,"baseline_adjusted_skill":0.16891935183725337,"baseline_adjusted_score":0.16891935183725337}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.0614284839625725,"accuracy":0.8292500000000002,"positive_recall":0.15414012738853503,"specificity":0.994090202177294,"precision":0.8642857142857142,"balanced_accuracy":0.5741151647829146,"f1":0.2616216216216216,"true_positive":12.1,"false_positive":1.9,"false_negative":66.4,"true_negative":319.6,"positive_prevalence":0.19625,"majority_accuracy_baseline":0.80375,"constant_brier_baseline":0.09878593749999999,"brier_skill":0.3781657033667114,"baseline_adjusted_skill":0.14823032956582916,"baseline_adjusted_score":0.14823032956582916}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.1863770371270519,"normalized_score_rmse":0.23833973121323662,"constant_score_baseline":0,"constant_mae_baseline":0.21125,"baseline_adjusted_skill":0.11774183608496147,"baseline_adjusted_score":0.11774183608496147}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.0790938040508597,"accuracy":0.7033163265306124,"positive_recall":0.8016014234875444,"specificity":0.6291405550581917,"precision":0.619954128440367,"balanced_accuracy":0.715370989272868,"f1":0.699172271081221,"true_positive":135.15,"false_positive":82.85,"false_negative":33.45,"true_negative":140.55,"positive_prevalence":0.4301020408163265,"majority_accuracy_baseline":0.5698979591836735,"constant_brier_baseline":0.12359641815910039,"brier_skill":0.36006394660203156,"baseline_adjusted_skill":0.43074197854573604,"baseline_adjusted_score":0.43074197854573604}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.18166204859087703,"normalized_score_rmse":0.2329903531380934,"constant_score_baseline":0.5,"constant_mae_baseline":0.2755102040816326,"baseline_adjusted_skill":0.3406340458553352,"baseline_adjusted_score":0.3406340458553352}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.04360698690101625,"accuracy":0.900625,"positive_recall":0.6003147128245476,"specificity":0.9573487888244909,"precision":0.7266666666666667,"balanced_accuracy":0.7788317508245193,"f1":0.6574752261956054,"true_positive":76.3,"false_positive":28.7,"false_negative":50.8,"true_negative":644.2,"positive_prevalence":0.158875,"majority_accuracy_baseline":0.841125,"constant_brier_baseline":0.09877748437499999,"brier_skill":0.5585331295190088,"baseline_adjusted_skill":0.5576635016490386,"baseline_adjusted_score":0.5576635016490386}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.17281445498555503,"normalized_score_rmse":0.2145067688512978,"constant_score_baseline":0,"constant_mae_baseline":0.165,"baseline_adjusted_skill":-0.04736033324578792,"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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"normalized_expected_score_mae":0.042790568349414644,"normalized_score_rmse":0.08695586044286595,"constant_score_baseline":0.1111111111111111,"constant_mae_baseline":0.10629629629629629,"baseline_adjusted_skill":0.5974406461901758,"baseline_adjusted_score":0.5974406461901758}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.55,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.38,"baseline_adjusted_skill":0.27419354838709686,"baseline_adjusted_score":0.27419354838709686}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.28426260960132,"accuracy":0.55,"positive_recall":0.34,"specificity":0.76,"precision":0.5862068965517241,"balanced_accuracy":0.55,"f1":0.43037974683544306,"true_positive":17,"false_positive":12,"false_negative":33,"true_negative":38,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":-0.13705043840527997,"baseline_adjusted_skill":0.10000000000000009,"baseline_adjusted_score":0.10000000000000009}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.35917826375082834,"uniform_accuracy_baseline":0.058823529411764705,"fixed_answer_accuracy_baseline":0.14910536779324055,"baseline_adjusted_skill":0.2468847352024922,"baseline_adjusted_score":0.2468847352024922}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.2838911213350167,"accuracy":0.5266666666666666,"positive_recall":0.1896551724137931,"specificity":0.9920634920634921,"precision":0.9705882352941176,"balanced_accuracy":0.5908593322386426,"f1":0.3173076923076923,"true_positive":33,"false_positive":1,"false_negative":141,"true_negative":125,"positive_prevalence":0.58,"majority_accuracy_baseline":0.58,"constant_brier_baseline":0.24359999999999998,"brier_skill":-0.1653986918514645,"baseline_adjusted_skill":0.18171866447728524,"baseline_adjusted_score":0.18171866447728524}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.16521610507246334,"accuracy":0.7566666666666667,"positive_recall":0.8280254777070064,"specificity":0.6783216783216783,"precision":0.7386363636363636,"balanced_accuracy":0.7531735780143424,"f1":0.7807807807807807,"true_positive":130,"false_positive":46,"false_negative":27,"true_negative":97,"positive_prevalence":0.5233333333333333,"majority_accuracy_baseline":0.5233333333333333,"constant_brier_baseline":0.24945555555555557,"brier_skill":0.3376932227285332,"baseline_adjusted_skill":0.5063471560286847,"baseline_adjusted_score":0.5063471560286847}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.5,"fixed_answer_accuracy_baseline":0.54,"baseline_adjusted_skill":0.8478260869565218,"baseline_adjusted_score":0.8478260869565218}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

Published measured S1MB run; community execution/submission status is not assumed independent. All published diagnostics: {"binary_brier":0.19311887259414,"accuracy":0.66,"positive_recall":0.72,"specificity":0.6,"precision":0.6428571428571429,"balanced_accuracy":0.6599999999999999,"f1":0.6792452830188679,"true_positive":36,"false_positive":20,"false_negative":14,"true_negative":30,"positive_prevalence":0.5,"majority_accuracy_baseline":0.5,"constant_brier_baseline":0.25,"brier_skill":0.22752450962343995,"baseline_adjusted_skill":0.31999999999999984,"baseline_adjusted_score":0.31999999999999984}. 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/OneJev1.6-9B; adapter onejev; settings {"questions_per_call": 1}. Run OmniJev__OneJev1.6-9B.

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":0.58,"uniform_accuracy_baseline":0.33333333333333326,"fixed_answer_accuracy_baseline":0.37,"baseline_adjusted_skill":0.33333333333333326,"baseline_adjusted_score":0.33333333333333326}. 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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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 9BOmniJev/OneJev1.6-9B.

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