Examenos

Correct answers over all 2,157 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 2157

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Equal-weight mean over the 43 categories.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 2157

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Accuracy on the 140 questions new in v4.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 140

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Correct answers over usable responses only; shown beside coverage.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 2157

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Share of the 2,157 inputs with a usable response.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 2157

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Pooled primary client time, network and failed requests included.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 2157

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Pooled primary client time, network and failed requests included.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 2157

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Lookup and filtering: 43 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 43

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Forward conditionals: 46 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 46

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Necessary conditions: 52 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 52

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Boolean scope: 54 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 54

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Quantifiers and sets: 49 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 49

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Comparisons: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Scheduling: 76 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 76

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

One-to-one assignments: 67 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 67

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Exact truth counting: 71 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 71

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Truth-teller consistency: 74 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 74

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Sufficiency and inconsistency: 41 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 41

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Object swaps: 52 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 52

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Sequential procedures: 48 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 48

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Temporal intervals: 42 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 42

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Spatial tracking: 49 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 49

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Reference binding: 50 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 50

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Beliefs and perspectives: 50 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 50

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Causal intervention: 50 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 50

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Exceptions and priorities: 58 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 58

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Planning: 43 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 43

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Directed reachability: 43 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 43

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Preference ordering: 51 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 51

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Rule counterexamples: 52 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 52

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Authority and stale records: 43 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 43

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Fault diagnosis: 50 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 50

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Probabilistic risk: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Value of information: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Robust decisions without a prior: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Strategic decisions: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Concurrent-history consistency: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Information-flow security: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Numerical pattern recognition: 23 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 23

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Quantitative reasoning: 200 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 200

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Understanding requests and routing: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Recognizing multiple requested actions: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Tracking current conversational intention: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Selecting a tool or requesting clarification: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Checking authorization and scope: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Making decisions with untrusted content: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Applying a contextual content policy: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Extracting and normalizing facts: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Checking claims against supplied evidence: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Assigning severity or priority from a rubric: 40 questions.

Super Decider · thinking off requested · direct API; Hosted native; collected 2026-11-05 to 2026-11-05 America/Toronto (1 days); one primary response per input, no scored retries. Identity: Exact provider-returned model identifier; hidden weights and effective thinking mode are not independently attested.

Thinking off was requested; the API does not attest the effective mode. The account catalogue labelled the model Free, so the tariff estimate may not apply.

Development benchmark, not an independently sampled test: 2,157 questions in 43 categories, the unchanged 2,017-question v3 bank plus 140 AQuA questions with source keys. The 23 numerical-pattern (MAIQ) and 200 quantitative (AQuA) questions are borrowed; the rest is predominantly project-developed with model-guided development, and Jev plus retained Microsoft and Drex feedback are development exposure. The AQuA additions were selected for misses by Fastino, Mammoth, GPT-6 Sol, D3 Ultra and Drex Max, which spreads but does not remove selection bias. Earlier primary responses are retained and newly added inputs were collected in later sessions, so one configuration can span several dates and routes. Strict accuracy counts an unusable response as not correct in the fixed denominator. Timing pools primary client times with the network included. The scoring key is private. A different number from v2 is a new bank, not a model change. Not ranked here.

Checked / reported: 2026-11-08 · Samples: 40

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

Estimate from a published tariff for calls without a reported charge, in USD per 1,000 questions; kept apart from reported charges.

Super Decider · thinking off requested · direct API; System 1 v4 ledger.

2157 calls at a published tariff out of 2,157.

Tariff-based estimate from the same ledger. Known run subtotal divided by 2,157 and multiplied by 1,000, not the bill for a separate 1,000-call run. A partial value is only the known subtotal: missing charges stay missing, so the true cost is higher by an unknown amount. Providers, routes, dates and access terms differ; these are not current tariffs. Free public access is not a price and has no row. Development benchmark; not ranked here.

Checked / reported: 2026-11-08 · Samples: 2157

Snapshot: 2026-11-06 · Revision: 224ee46dc1c16a8ecf2c154a2144b4d2fdc45de1 · Published summary observations; upstream task/result terms retained (AQuA-RAT Apache-2.0; MAIQ declared MIT, original question rights not established)

When2Call (call a tool, ask, or decline), Decision Index 0.3 version.

Super Decider, default thinking ("auto"), as published in the README; the README does not pin a weights commit for these runs.

Printed in the vendor’s own README table.

Singularity Compute’s own runs in the Super Decider README (commit d1a96b1). When2Call, PhishNChips and BFCL are the Decision Index 0.3 versions, run on every row with the Decision Index kit. The README’s Jev and Clef columns are copied from public leaderboards, not peer runs, so they are not stored here.

Checked / reported: 2026-11-08 · Samples: Not published

Snapshot: 2026-10-15 · Revision: d1a96b1 · Published observations; result reuse terms not specified

PhishNChips (should an email agent follow this link), Decision Index 0.3 version.

Super Decider, default thinking ("auto"), as published in the README; the README does not pin a weights commit for these runs.

Printed in the vendor’s own README table.

Singularity Compute’s own runs in the Super Decider README (commit d1a96b1). When2Call, PhishNChips and BFCL are the Decision Index 0.3 versions, run on every row with the Decision Index kit. The README’s Jev and Clef columns are copied from public leaderboards, not peer runs, so they are not stored here.

Checked / reported: 2026-11-08 · Samples: Not published

Snapshot: 2026-10-15 · Revision: d1a96b1 · Published observations; result reuse terms not specified

BFCL tool selection (which functions to call), Decision Index 0.3 version.

Super Decider, default thinking ("auto"), as published in the README; the README does not pin a weights commit for these runs.

Printed in the vendor’s own README table.

Singularity Compute’s own runs in the Super Decider README (commit d1a96b1). When2Call, PhishNChips and BFCL are the Decision Index 0.3 versions, run on every row with the Decision Index kit. The README’s Jev and Clef columns are copied from public leaderboards, not peer runs, so they are not stored here.

Checked / reported: 2026-11-08 · Samples: Not published

Snapshot: 2026-10-15 · Revision: d1a96b1 · Published observations; result reuse terms not specified

Hanno Labs DecisionBench, 23,900 decisions.

Super Decider, default thinking ("auto"), as published in the README; the README does not pin a weights commit for these runs.

Printed in the vendor’s own README table.

Singularity Compute’s own runs in the Super Decider README (commit d1a96b1). When2Call, PhishNChips and BFCL are the Decision Index 0.3 versions, run on every row with the Decision Index kit. The README’s Jev and Clef columns are copied from public leaderboards, not peer runs, so they are not stored here.

Checked / reported: 2026-11-08 · Samples: 23900

Snapshot: 2026-10-15 · Revision: d1a96b1 · Published observations; result reuse terms not specified

Singularity Compute’s own held-out set of 1,119 long documents from domains not seen in training.

Super Decider, default thinking ("auto"), as published in the README; the README does not pin a weights commit for these runs.

Printed in the vendor’s own README table.

Singularity Compute’s own runs in the Super Decider README (commit d1a96b1). When2Call, PhishNChips and BFCL are the Decision Index 0.3 versions, run on every row with the Decision Index kit. The README’s Jev and Clef columns are copied from public leaderboards, not peer runs, so they are not stored here.

Checked / reported: 2026-11-08 · Samples: 1119

Snapshot: 2026-10-15 · Revision: d1a96b1 · Published observations; result reuse terms not specified

Capability Score on the rendered board.

Super Decider · Open weights · diffusion LM. Board key singularity-super-decider; method tag v1.7. Measured on the Second regular draw (v1.7.0), 2026-10-21; put on the v1.6.1 scale by the draw's anchor offset (see How it works). Source link https://singularitycompute.com/super-decider.

Rendered board row. Measured through Singularity Compute’s hosted API on 21 October with default thinking; the row names no weights commit. The same board also has the thinking-always row (singularity-super-decider-thinking) at capability 85.852, kept in published metrics.

Benchmark Heaven's rendered board, read 2 November 2026: 283 ranked systems · 1,500 decisions each (600 for 19 equated API re-runs) · 131 newer ranked rows tagged with their draw · 14 older rows dated separately. Newer rows are measured on dated draws and put on the v1.6.1 scale by the draw's anchor offset, so a row's draw is part of its identity. Distinct from Leanmcp JevBench, the community Decision Index and the stored Benchmark Heaven v1.6.1 feed. Cost is the source's model on a GPU-time basis for self-hosted rows, not a provider tariff. Self-hosted latency is timed on the GPU over loopback and API latency end to end with the network; the source says they are not directly comparable, so they stay in separate datasets. No Examenos recomputation.

Checked / reported: 2026-11-08 · Evaluated: 2026-10-21 · Samples: Not published

Snapshot: 2026-10-31 · Revision: Board v1.7.48, method v1.8, updated 2026-10-31; page sha256 df9093384c9cdf5854e065f71dd3abd83a127793f22f4ca70268e9981e0a0b17 · Published summary observations; upstream task/result terms retained

Intelligence on the rendered board.

Super Decider · Open weights · diffusion LM. Board key singularity-super-decider; method tag v1.7. Measured on the Second regular draw (v1.7.0), 2026-10-21; put on the v1.6.1 scale by the draw's anchor offset (see How it works). Source link https://singularitycompute.com/super-decider.

Rendered board row. Measured through Singularity Compute’s hosted API on 21 October with default thinking; the row names no weights commit. The same board also has the thinking-always row (singularity-super-decider-thinking) at capability 85.852, kept in published metrics.

Benchmark Heaven's rendered board, read 2 November 2026: 283 ranked systems · 1,500 decisions each (600 for 19 equated API re-runs) · 131 newer ranked rows tagged with their draw · 14 older rows dated separately. Newer rows are measured on dated draws and put on the v1.6.1 scale by the draw's anchor offset, so a row's draw is part of its identity. Distinct from Leanmcp JevBench, the community Decision Index and the stored Benchmark Heaven v1.6.1 feed. Cost is the source's model on a GPU-time basis for self-hosted rows, not a provider tariff. Self-hosted latency is timed on the GPU over loopback and API latency end to end with the network; the source says they are not directly comparable, so they stay in separate datasets. No Examenos recomputation.

Checked / reported: 2026-11-08 · Evaluated: 2026-10-21 · Samples: Not published

Snapshot: 2026-10-31 · Revision: Board v1.7.48, method v1.8, updated 2026-10-31; page sha256 df9093384c9cdf5854e065f71dd3abd83a127793f22f4ca70268e9981e0a0b17 · Published summary observations; upstream task/result terms retained

Calibration on the rendered board.

Super Decider · Open weights · diffusion LM. Board key singularity-super-decider; method tag v1.7. Measured on the Second regular draw (v1.7.0), 2026-10-21; put on the v1.6.1 scale by the draw's anchor offset (see How it works). Source link https://singularitycompute.com/super-decider.

Rendered board row. Measured through Singularity Compute’s hosted API on 21 October with default thinking; the row names no weights commit. The same board also has the thinking-always row (singularity-super-decider-thinking) at capability 85.852, kept in published metrics.

Benchmark Heaven's rendered board, read 2 November 2026: 283 ranked systems · 1,500 decisions each (600 for 19 equated API re-runs) · 131 newer ranked rows tagged with their draw · 14 older rows dated separately. Newer rows are measured on dated draws and put on the v1.6.1 scale by the draw's anchor offset, so a row's draw is part of its identity. Distinct from Leanmcp JevBench, the community Decision Index and the stored Benchmark Heaven v1.6.1 feed. Cost is the source's model on a GPU-time basis for self-hosted rows, not a provider tariff. Self-hosted latency is timed on the GPU over loopback and API latency end to end with the network; the source says they are not directly comparable, so they stay in separate datasets. No Examenos recomputation.

Checked / reported: 2026-11-08 · Evaluated: 2026-10-21 · Samples: Not published

Snapshot: 2026-10-31 · Revision: Board v1.7.48, method v1.8, updated 2026-10-31; page sha256 df9093384c9cdf5854e065f71dd3abd83a127793f22f4ca70268e9981e0a0b17 · Published summary observations; upstream task/result terms retained

Cost Score on the rendered board.

Super Decider · Open weights · diffusion LM. Board key singularity-super-decider; method tag v1.7. Measured on the Second regular draw (v1.7.0), 2026-10-21; put on the v1.6.1 scale by the draw's anchor offset (see How it works). Source link https://singularitycompute.com/super-decider.

Rendered board row. Measured through Singularity Compute’s hosted API on 21 October with default thinking; the row names no weights commit. The same board also has the thinking-always row (singularity-super-decider-thinking) at capability 85.852, kept in published metrics.

Benchmark Heaven's rendered board, read 2 November 2026: 283 ranked systems · 1,500 decisions each (600 for 19 equated API re-runs) · 131 newer ranked rows tagged with their draw · 14 older rows dated separately. Newer rows are measured on dated draws and put on the v1.6.1 scale by the draw's anchor offset, so a row's draw is part of its identity. Distinct from Leanmcp JevBench, the community Decision Index and the stored Benchmark Heaven v1.6.1 feed. Cost is the source's model on a GPU-time basis for self-hosted rows, not a provider tariff. Self-hosted latency is timed on the GPU over loopback and API latency end to end with the network; the source says they are not directly comparable, so they stay in separate datasets. No Examenos recomputation.

Checked / reported: 2026-11-08 · Evaluated: 2026-10-21 · Samples: Not published

Snapshot: 2026-10-31 · Revision: Board v1.7.48, method v1.8, updated 2026-10-31; page sha256 df9093384c9cdf5854e065f71dd3abd83a127793f22f4ca70268e9981e0a0b17 · Published summary observations; upstream task/result terms retained

Modelled cost per 1,000 decisions on the rendered board.

Super Decider · Open weights · diffusion LM. Board key singularity-super-decider; method tag v1.7. Measured on the Second regular draw (v1.7.0), 2026-10-21; put on the v1.6.1 scale by the draw's anchor offset (see How it works). Source link https://singularitycompute.com/super-decider.

Rendered board row. Measured through Singularity Compute’s hosted API on 21 October with default thinking; the row names no weights commit. The same board also has the thinking-always row (singularity-super-decider-thinking) at capability 85.852, kept in published metrics.

Benchmark Heaven's rendered board, read 2 November 2026: 283 ranked systems · 1,500 decisions each (600 for 19 equated API re-runs) · 131 newer ranked rows tagged with their draw · 14 older rows dated separately. Newer rows are measured on dated draws and put on the v1.6.1 scale by the draw's anchor offset, so a row's draw is part of its identity. Distinct from Leanmcp JevBench, the community Decision Index and the stored Benchmark Heaven v1.6.1 feed. Cost is the source's model on a GPU-time basis for self-hosted rows, not a provider tariff. Self-hosted latency is timed on the GPU over loopback and API latency end to end with the network; the source says they are not directly comparable, so they stay in separate datasets. No Examenos recomputation.

Checked / reported: 2026-11-08 · Evaluated: 2026-10-21 · Samples: Not published

Snapshot: 2026-10-31 · Revision: Board v1.7.48, method v1.8, updated 2026-10-31; page sha256 df9093384c9cdf5854e065f71dd3abd83a127793f22f4ca70268e9981e0a0b17 · Published summary observations; upstream task/result terms retained

API latency, end to end on the rendered board.

Super Decider · Open weights · diffusion LM. Board key singularity-super-decider; method tag v1.7. Measured on the Second regular draw (v1.7.0), 2026-10-21; put on the v1.6.1 scale by the draw's anchor offset (see How it works). Source link https://singularitycompute.com/super-decider.

Rendered board row. Measured through Singularity Compute’s hosted API on 21 October with default thinking; the row names no weights commit. The same board also has the thinking-always row (singularity-super-decider-thinking) at capability 85.852, kept in published metrics.

Benchmark Heaven's rendered board, read 2 November 2026: 283 ranked systems · 1,500 decisions each (600 for 19 equated API re-runs) · 131 newer ranked rows tagged with their draw · 14 older rows dated separately. Newer rows are measured on dated draws and put on the v1.6.1 scale by the draw's anchor offset, so a row's draw is part of its identity. Distinct from Leanmcp JevBench, the community Decision Index and the stored Benchmark Heaven v1.6.1 feed. Cost is the source's model on a GPU-time basis for self-hosted rows, not a provider tariff. Self-hosted latency is timed on the GPU over loopback and API latency end to end with the network; the source says they are not directly comparable, so they stay in separate datasets. No Examenos recomputation.

Checked / reported: 2026-11-08 · Evaluated: 2026-10-21 · Samples: Not published

Snapshot: 2026-10-31 · Revision: Board v1.7.48, method v1.8, updated 2026-10-31; page sha256 df9093384c9cdf5854e065f71dd3abd83a127793f22f4ca70268e9981e0a0b17 · Published summary observations; upstream task/result terms retained