{"schema_version":1,"total":538,"offset":0,"limit":100,"observations":[{"id":"aa:0081ab31-d10a-44a0-a10d-eee5533fec65:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0081ab31-d10a-44a0-a10d-eee5533fec65","name":"GLM-4.5V (Non-reasoning)","model_id":"glm-4.5v::non-reasoning","variant":null,"harness":null},"value":-55.5833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0081ab31-d10a-44a0-a10d-eee5533fec65; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0097ebf5-124f-42f6-9463-33b00e711f03:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0097ebf5-124f-42f6-9463-33b00e711f03","name":"Gemini 3.5 Flash (high)","model_id":"gemini-3.5-flash::high","variant":"high","harness":null},"value":21.1833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0097ebf5-124f-42f6-9463-33b00e711f03; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort high","comparison_key":null},{"id":"aa:00f1248e-78e3-4230-8dc8-5e13ba8645e2:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"00f1248e-78e3-4230-8dc8-5e13ba8645e2","name":"MiMo-V2.5-Pro","model_id":"mimo-v2.5-pro::reasoning","variant":null,"harness":null},"value":3.25,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 00f1248e-78e3-4230-8dc8-5e13ba8645e2; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0121d27b-5b8a-4901-8684-80589cc6d40d:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0121d27b-5b8a-4901-8684-80589cc6d40d","name":"JT-35B-Flash","model_id":"jt-35b-flash::default","variant":null,"harness":null},"value":-24.2166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0121d27b-5b8a-4901-8684-80589cc6d40d; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:016d330a-2141-4afa-b2fc-62b314423dc1:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"016d330a-2141-4afa-b2fc-62b314423dc1","name":"Mercury 2","model_id":"mercury-2::default","variant":"high","harness":null},"value":-50.7166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 016d330a-2141-4afa-b2fc-62b314423dc1; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort high","comparison_key":null},{"id":"aa:0179b427-93dc-415c-bb4c-f980ddf8d088:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0179b427-93dc-415c-bb4c-f980ddf8d088","name":"Qwen3.5 Omni Plus","model_id":"qwen3.5-omni-plus::default","variant":null,"harness":null},"value":-13.1166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0179b427-93dc-415c-bb4c-f980ddf8d088; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:018c60e8-e908-431a-ba57-c840b1df3987:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"018c60e8-e908-431a-ba57-c840b1df3987","name":"Nova 2.0 Omni (medium)","model_id":"nova-2.0-omni::medium","variant":"medium","harness":null},"value":-59.0833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 018c60e8-e908-431a-ba57-c840b1df3987; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort medium","comparison_key":null},{"id":"aa:019e86f6-e66b-42d8-8a50-235a06b53003:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"019e86f6-e66b-42d8-8a50-235a06b53003","name":"GPT-5.2 Codex (xhigh)","model_id":"gpt-5.2-codex::xhigh","variant":"xhigh","harness":null},"value":-2.16666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 019e86f6-e66b-42d8-8a50-235a06b53003; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort xhigh","comparison_key":null},{"id":"aa:021b1b31-d2fc-4653-ab74-c10bd2f41c8e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"021b1b31-d2fc-4653-ab74-c10bd2f41c8e","name":"Qwen3.5 122B A10B (Non-reasoning)","model_id":"qwen3.5-122b-a10b::non-reasoning","variant":null,"harness":null},"value":-54.9666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 021b1b31-d2fc-4653-ab74-c10bd2f41c8e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:025ec6b6-df4a-449f-9a03-24e4388d6863:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"025ec6b6-df4a-449f-9a03-24e4388d6863","name":"Gemma 4 12B (Non-reasoning)","model_id":"gemma-4-12b::non-reasoning","variant":null,"harness":null},"value":-52.8,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 025ec6b6-df4a-449f-9a03-24e4388d6863; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:033ade17-d9ec-44e0-b792-b5f1fcd5ab4c:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"033ade17-d9ec-44e0-b792-b5f1fcd5ab4c","name":"Gemini 3.5 Flash (minimal)","model_id":"gemini-3.5-flash::minimal","variant":"minimal","harness":null},"value":0.666666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 033ade17-d9ec-44e0-b792-b5f1fcd5ab4c; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort minimal","comparison_key":null},{"id":"aa:033e4aa9-a556-4224-87b0-341ed1070257:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"033e4aa9-a556-4224-87b0-341ed1070257","name":"Claude 3.5 Haiku","model_id":"claude-3.5-haiku::default","variant":null,"harness":null},"value":-22.5166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 033e4aa9-a556-4224-87b0-341ed1070257; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:04781a0e-40f0-4e2a-a4e5-18e389364a79:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"04781a0e-40f0-4e2a-a4e5-18e389364a79","name":"Gemma 3 270M","model_id":"gemma-3-270m::default","variant":null,"harness":null},"value":-29.2666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 04781a0e-40f0-4e2a-a4e5-18e389364a79; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:04787c2b-0751-4269-8029-075b727d7aed:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"04787c2b-0751-4269-8029-075b727d7aed","name":"Grok 4.20 0309 (Reasoning)","model_id":"grok-4.20-0309::reasoning","variant":null,"harness":null},"value":12.95,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 04787c2b-0751-4269-8029-075b727d7aed; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:04d023f3-025c-4d78-9571-53edda3eaf2a:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"04d023f3-025c-4d78-9571-53edda3eaf2a","name":"GPT-5.1 Codex (high)","model_id":"gpt-5.1-codex::high","variant":"high","harness":null},"value":-6.5,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 04d023f3-025c-4d78-9571-53edda3eaf2a; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort high","comparison_key":null},{"id":"aa:04ee6719-0327-463b-a1a1-70a6a78254f9:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"04ee6719-0327-463b-a1a1-70a6a78254f9","name":"Muse Spark 1.2 (xhigh)","model_id":"muse-spark-1.2::xhigh","variant":"xhigh","harness":null},"value":27.2,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 04ee6719-0327-463b-a1a1-70a6a78254f9; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort xhigh","comparison_key":null},{"id":"aa:050c61cd-cddc-463a-a30a-a82aaa37be59:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"050c61cd-cddc-463a-a30a-a82aaa37be59","name":"GPT-5.6 Luna (low)","model_id":"gpt-5.6-luna::low","variant":"low","harness":null},"value":-14.65,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 050c61cd-cddc-463a-a30a-a82aaa37be59; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort low","comparison_key":null},{"id":"aa:05776db7-f5c0-40f7-b824-079160f8cfa8:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"05776db7-f5c0-40f7-b824-079160f8cfa8","name":"Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)","model_id":"claude-fable-5.1::low","variant":"low","harness":null},"value":34.1333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 05776db7-f5c0-40f7-b824-079160f8cfa8; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort low","comparison_key":null},{"id":"aa:05a32e26-e609-4377-951b-8fa23d329926:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"05a32e26-e609-4377-951b-8fa23d329926","name":"Mistral Medium 3.1","model_id":"mistral-medium-3.1::default","variant":null,"harness":null},"value":-46.2833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 05a32e26-e609-4377-951b-8fa23d329926; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:05e45a36-b5c6-47a1-8adb-9ddc19add5b3:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"05e45a36-b5c6-47a1-8adb-9ddc19add5b3","name":"GPT-5 nano (minimal)","model_id":"gpt-5-nano::minimal","variant":"minimal","harness":null},"value":-64.0666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 05e45a36-b5c6-47a1-8adb-9ddc19add5b3; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort minimal","comparison_key":null},{"id":"aa:076f2674-bc4b-4925-be59-50832eb8c090:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"076f2674-bc4b-4925-be59-50832eb8c090","name":"o3-mini (high)","model_id":"o3-mini::high","variant":"high","harness":null},"value":-42.5666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 076f2674-bc4b-4925-be59-50832eb8c090; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort high","comparison_key":null},{"id":"aa:07c35e00-2b12-44c8-91cc-408629cd569e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"07c35e00-2b12-44c8-91cc-408629cd569e","name":"DeepSeek V3.2 Exp (Non-reasoning)","model_id":"deepseek-v3.2-exp::non-reasoning","variant":null,"harness":null},"value":-48.2,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 07c35e00-2b12-44c8-91cc-408629cd569e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:08242385-ee91-4de6-be7f-271a6d9780ce:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"08242385-ee91-4de6-be7f-271a6d9780ce","name":"Apodex 1.1","model_id":"apodex-1.1::default","variant":null,"harness":null},"value":-21.9,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 08242385-ee91-4de6-be7f-271a6d9780ce; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0904b596-8932-43bd-9b21-324f128e1723:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0904b596-8932-43bd-9b21-324f128e1723","name":"GPT-5.6 Sol (low)","model_id":"gpt-5.6-sol::low","variant":"low","harness":null},"value":18.8666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0904b596-8932-43bd-9b21-324f128e1723; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort low","comparison_key":null},{"id":"aa:093883ed-f5fc-443b-8e18-afbfb166699e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"093883ed-f5fc-443b-8e18-afbfb166699e","name":"Qwen3 Coder 480B A35B Instruct","model_id":"qwen3-coder-480b-a35b-instruct::default","variant":null,"harness":null},"value":-22.2,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 093883ed-f5fc-443b-8e18-afbfb166699e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:093b9df2-ebee-4309-943f-5a7e88360adf:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"093b9df2-ebee-4309-943f-5a7e88360adf","name":"Gemini 3.5 Flash-Lite","model_id":"gemini-3.5-flash-lite::default","variant":"high","harness":null},"value":5.23333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 093b9df2-ebee-4309-943f-5a7e88360adf; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort high","comparison_key":null},{"id":"aa:0985ada8-2ed8-404d-bd8b-7357666ce40f:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0985ada8-2ed8-404d-bd8b-7357666ce40f","name":"Qwen3.5 2B (Non-reasoning)","model_id":"qwen3.5-2b::non-reasoning","variant":null,"harness":null},"value":-83.1333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0985ada8-2ed8-404d-bd8b-7357666ce40f; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:09f43999-b67b-4c1b-b050-44df41ed7e62:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"09f43999-b67b-4c1b-b050-44df41ed7e62","name":"Devstral 2","model_id":"devstral-2-123b::default","variant":null,"harness":null},"value":-46.7,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 09f43999-b67b-4c1b-b050-44df41ed7e62; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0a7dda4d-cc9c-4a90-abc1-abb5772c901b:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0a7dda4d-cc9c-4a90-abc1-abb5772c901b","name":"DeepSeek V3.1 Terminus (Reasoning)","model_id":"deepseek-v3.1-terminus::reasoning","variant":null,"harness":null},"value":-26.4,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0a7dda4d-cc9c-4a90-abc1-abb5772c901b; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0b226b82-1462-4860-bf1a-f8aed7024791:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0b226b82-1462-4860-bf1a-f8aed7024791","name":"Qwen3 Omni 30B A3B Instruct","model_id":"qwen3-omni-30b-a3b-instruct::default","variant":null,"harness":null},"value":-69.2666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0b226b82-1462-4860-bf1a-f8aed7024791; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0b7efa66-2115-49e0-a1b7-a2ba225fe9f6:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0b7efa66-2115-49e0-a1b7-a2ba225fe9f6","name":"Grok Build 0.1 0616","model_id":"grok-build-0.1-0616::default","variant":null,"harness":null},"value":6.36666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0b7efa66-2115-49e0-a1b7-a2ba225fe9f6; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0c64b008-20c3-408d-bd68-15136df8cd2c:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0c64b008-20c3-408d-bd68-15136df8cd2c","name":"Granite 4.2 3B","model_id":"granite-4.2-3b::default","variant":null,"harness":null},"value":-14.7166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0c64b008-20c3-408d-bd68-15136df8cd2c; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0d94dc87-12c8-4d4a-8d99-804ce3f17bc2:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0d94dc87-12c8-4d4a-8d99-804ce3f17bc2","name":"Nova 2.0 Pro Preview (medium)","model_id":"nova-2.0-pro-preview::medium","variant":"medium","harness":null},"value":-49.05,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0d94dc87-12c8-4d4a-8d99-804ce3f17bc2; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort medium","comparison_key":null},{"id":"aa:0de09623-2b1a-4c8d-86ef-7f5245d4e24b:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0de09623-2b1a-4c8d-86ef-7f5245d4e24b","name":"Inkling (xhigh)","model_id":"inkling::xhigh","variant":"xhigh","harness":null},"value":2,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0de09623-2b1a-4c8d-86ef-7f5245d4e24b; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort xhigh","comparison_key":null},{"id":"aa:0de67206-4d36-4d10-b8f6-cf37fa747a03:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0de67206-4d36-4d10-b8f6-cf37fa747a03","name":"Kimi K2.6","model_id":"kimi-k2.6::reasoning","variant":null,"harness":null},"value":5.3,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0de67206-4d36-4d10-b8f6-cf37fa747a03; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0e34f05c-387e-4968-be15-ccec4a55d8c1:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0e34f05c-387e-4968-be15-ccec4a55d8c1","name":"DeepSeek R1 (Jan '25)","model_id":"deepseek-r1-jan-25::default","variant":null,"harness":null},"value":-32.2166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0e34f05c-387e-4968-be15-ccec4a55d8c1; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0e5f6140-1154-4583-a3e0-8c032a338892:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0e5f6140-1154-4583-a3e0-8c032a338892","name":"Qwen3 0.6B (Non-reasoning)","model_id":"qwen3-0.6b::non-reasoning","variant":null,"harness":null},"value":-84.95,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0e5f6140-1154-4583-a3e0-8c032a338892; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0e66bae9-41f1-42fc-9276-ce8cb6f72919:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0e66bae9-41f1-42fc-9276-ce8cb6f72919","name":"Qwen3.5 397B A17B (Reasoning)","model_id":"qwen3.5-397b-a17b::reasoning","variant":null,"harness":null},"value":-30.75,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0e66bae9-41f1-42fc-9276-ce8cb6f72919; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0faadeeb-320c-45cf-9c76-5f8768f342e6:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0faadeeb-320c-45cf-9c76-5f8768f342e6","name":"LFM2 1.2B","model_id":"lfm2-1.2b::default","variant":null,"harness":null},"value":-72.4333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0faadeeb-320c-45cf-9c76-5f8768f342e6; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0fc6308e-fbd2-42d3-a216-06da3c43e34e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0fc6308e-fbd2-42d3-a216-06da3c43e34e","name":"Kimi K2.6 (Non-reasoning)","model_id":"kimi-k2.6::non-reasoning","variant":null,"harness":null},"value":-9.18333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0fc6308e-fbd2-42d3-a216-06da3c43e34e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:0fec07d5-a9b2-407a-b5f8-5bf10bd86b59:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"0fec07d5-a9b2-407a-b5f8-5bf10bd86b59","name":"Magistral Small 1","model_id":"magistral-small-1::default","variant":null,"harness":null},"value":-44.4,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 0fec07d5-a9b2-407a-b5f8-5bf10bd86b59; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1071dea1-43e7-4fe9-b936-3034bb622b2e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1071dea1-43e7-4fe9-b936-3034bb622b2e","name":"Granite 4.2 30B","model_id":"granite-4.2-30b::default","variant":null,"harness":null},"value":-12.9166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1071dea1-43e7-4fe9-b936-3034bb622b2e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:12adec16-19fe-4d92-aeff-5ef3eb7e780a:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"12adec16-19fe-4d92-aeff-5ef3eb7e780a","name":"MiniMax-M2.5","model_id":"minimax-m2.5::default","variant":null,"harness":null},"value":-38.8666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 12adec16-19fe-4d92-aeff-5ef3eb7e780a; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:12f6a061-0ab3-4c76-b225-49abee253651:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"12f6a061-0ab3-4c76-b225-49abee253651","name":"Mistral Small 4 (Non-reasoning)","model_id":"mistral-small-4::non-reasoning","variant":null,"harness":null},"value":-48.5166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 12f6a061-0ab3-4c76-b225-49abee253651; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1305c921-7aaa-4d6d-99b5-99b3acf15e19:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1305c921-7aaa-4d6d-99b5-99b3acf15e19","name":"Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)","model_id":"claude-opus-5::xhigh","variant":"xhigh","harness":null},"value":35.3833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1305c921-7aaa-4d6d-99b5-99b3acf15e19; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort xhigh","comparison_key":null},{"id":"aa:13358187-4584-479c-ab43-5bcdf8f297a4:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"13358187-4584-479c-ab43-5bcdf8f297a4","name":"Claude 3.7 Sonnet (Reasoning)","model_id":"claude-3.7-sonnet::reasoning","variant":null,"harness":null},"value":-0.733333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 13358187-4584-479c-ab43-5bcdf8f297a4; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:142b93bf-09c4-42dc-9c3a-50b1a222cbd4:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"142b93bf-09c4-42dc-9c3a-50b1a222cbd4","name":"Claude Sonnet 5 (Adaptive Reasoning, Low Effort)","model_id":"claude-sonnet-5::low","variant":"low","harness":null},"value":-8.23333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 142b93bf-09c4-42dc-9c3a-50b1a222cbd4; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort low","comparison_key":null},{"id":"aa:1479f50b-d37f-4b55-bb8b-4212a15042eb:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1479f50b-d37f-4b55-bb8b-4212a15042eb","name":"MiMo-V2-Flash (Feb 2026)","model_id":"mimo-v2-flash-feb-2026::default","variant":null,"harness":null},"value":-19.05,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1479f50b-d37f-4b55-bb8b-4212a15042eb; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:149096f3-57b7-4413-80c2-a2c010a2995a:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"149096f3-57b7-4413-80c2-a2c010a2995a","name":"GLM-5-Turbo","model_id":"glm-5-turbo::default","variant":null,"harness":null},"value":-16.3666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 149096f3-57b7-4413-80c2-a2c010a2995a; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:15b56b8e-7b93-4ed9-ac06-75c922e3b86e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"15b56b8e-7b93-4ed9-ac06-75c922e3b86e","name":"Ling-1T","model_id":"ling-1t::default","variant":null,"harness":null},"value":-55.1333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 15b56b8e-7b93-4ed9-ac06-75c922e3b86e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:16149b9c-a1e9-4669-a5cb-ff3c00d78f89:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"16149b9c-a1e9-4669-a5cb-ff3c00d78f89","name":"gpt-oss-20b (low)","model_id":"gpt-oss-20b::low","variant":"low","harness":null},"value":-58.55,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 16149b9c-a1e9-4669-a5cb-ff3c00d78f89; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort low","comparison_key":null},{"id":"aa:169e47f5-3d4d-4ad4-8f8b-ab46f0c73f67:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"169e47f5-3d4d-4ad4-8f8b-ab46f0c73f67","name":"Qwen3.5 27B (Reasoning)","model_id":"qwen3.5-27b::reasoning","variant":null,"harness":null},"value":-43.9833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 169e47f5-3d4d-4ad4-8f8b-ab46f0c73f67; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:16c5b637-8bce-4252-81f2-1b87a36a4e4c:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"16c5b637-8bce-4252-81f2-1b87a36a4e4c","name":"o3","model_id":"o3::default","variant":null,"harness":null},"value":-15.55,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 16c5b637-8bce-4252-81f2-1b87a36a4e4c; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:18721247-4e56-4cf7-9a9d-c71cc60c0961:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"18721247-4e56-4cf7-9a9d-c71cc60c0961","name":"K-EXAONE 2.0","model_id":"k-exaone-2.0::default","variant":null,"harness":null},"value":-6.6,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 18721247-4e56-4cf7-9a9d-c71cc60c0961; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:19496b81-9f41-4214-a77a-1df803b3c5ae:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"19496b81-9f41-4214-a77a-1df803b3c5ae","name":"GLM-5.3-Flash","model_id":"glm-5.3-flash::default","variant":"max","harness":null},"value":7.46666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 19496b81-9f41-4214-a77a-1df803b3c5ae; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort max","comparison_key":null},{"id":"aa:198b717f-42c8-4ab7-a699-ae9373d669d3:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"198b717f-42c8-4ab7-a699-ae9373d669d3","name":"DeepSeek V3.1 (Reasoning)","model_id":"deepseek-v3.1::reasoning","variant":null,"harness":null},"value":-29.5833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 198b717f-42c8-4ab7-a699-ae9373d669d3; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1a8ba535-df18-459b-ad40-3199191296d7:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1a8ba535-df18-459b-ad40-3199191296d7","name":"Llama 3.3 Nemotron Super 49B v1 (Reasoning)","model_id":"llama-3.3-nemotron-super-49b-v1::reasoning","variant":null,"harness":null},"value":-58.3,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1a8ba535-df18-459b-ad40-3199191296d7; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1aa3694e-b656-4dbe-8f84-0c65d8897abb:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1aa3694e-b656-4dbe-8f84-0c65d8897abb","name":"Step 3.5 Flash 2603","model_id":"step-3.5-flash-2603::default","variant":null,"harness":null},"value":-44.2166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1aa3694e-b656-4dbe-8f84-0c65d8897abb; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1b64aa81-c223-4b8f-909b-82185a234765:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1b64aa81-c223-4b8f-909b-82185a234765","name":"Solar Pro 4","model_id":"solar-pro-4::default","variant":null,"harness":null},"value":-0.85,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1b64aa81-c223-4b8f-909b-82185a234765; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1cf439b8-0cfd-47b2-9de2-9a2157e6762b:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1cf439b8-0cfd-47b2-9de2-9a2157e6762b","name":"GLM-4.5 (Reasoning)","model_id":"glm-4.5::reasoning","variant":null,"harness":null},"value":-27.3833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1cf439b8-0cfd-47b2-9de2-9a2157e6762b; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1d81aa1c-64c8-442a-9c41-81b37e407b91:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1d81aa1c-64c8-442a-9c41-81b37e407b91","name":"Gemini 2.5 Flash-Lite (Non-reasoning)","model_id":"gemini-2.5-flash-lite::non-reasoning","variant":null,"harness":null},"value":-58.7833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1d81aa1c-64c8-442a-9c41-81b37e407b91; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1e9907e0-ffac-4595-b006-962e4f1da7cf:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1e9907e0-ffac-4595-b006-962e4f1da7cf","name":"North Mini Code","model_id":"north-mini-code::default","variant":null,"harness":null},"value":-48.5833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1e9907e0-ffac-4595-b006-962e4f1da7cf; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1f054429-397e-4fdb-9e71-67bc92c1735e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1f054429-397e-4fdb-9e71-67bc92c1735e","name":"GPT-5.5 (xhigh)","model_id":"gpt-5.5::xhigh","variant":"xhigh","harness":null},"value":20.5166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1f054429-397e-4fdb-9e71-67bc92c1735e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort xhigh","comparison_key":null},{"id":"aa:1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3","name":"GPT-6 Astra (xhigh)","model_id":"gpt-6-astra::xhigh","variant":"xhigh","harness":null},"value":43.4166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort xhigh","comparison_key":null},{"id":"aa:1f6478c9-3e22-4586-adbe-841782859677:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1f6478c9-3e22-4586-adbe-841782859677","name":"Nova 2.0 Omni (Non-reasoning)","model_id":"nova-2.0-omni::non-reasoning","variant":null,"harness":null},"value":-64.2333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1f6478c9-3e22-4586-adbe-841782859677; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1fc32894-1060-493b-af94-62bb1068555e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1fc32894-1060-493b-af94-62bb1068555e","name":"Granite 4.0 Micro","model_id":"granite-4.0-micro::default","variant":null,"harness":null},"value":-77.5333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1fc32894-1060-493b-af94-62bb1068555e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:1fc54cef-d179-48b1-a27d-046874e9b208:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"1fc54cef-d179-48b1-a27d-046874e9b208","name":"Claude 3 Haiku","model_id":"claude-3-haiku::default","variant":null,"harness":null},"value":-48.6333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 1fc54cef-d179-48b1-a27d-046874e9b208; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:20928ba9-3a3f-415f-9519-b84ff64ecf34:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"20928ba9-3a3f-415f-9519-b84ff64ecf34","name":"Claude Opus 5 (Adaptive Reasoning, Low Effort)","model_id":"claude-opus-5::low","variant":"low","harness":null},"value":28.55,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 20928ba9-3a3f-415f-9519-b84ff64ecf34; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort low","comparison_key":null},{"id":"aa:20da3b31-fc0a-4359-abec-d59367bf1d9f:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"20da3b31-fc0a-4359-abec-d59367bf1d9f","name":"Qwen3.5 9B (Non-reasoning)","model_id":"qwen3.5-9b::non-reasoning","variant":null,"harness":null},"value":-70.7,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 20da3b31-fc0a-4359-abec-d59367bf1d9f; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:217b34ec-5920-4fc1-8886-6a70a324837d:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"217b34ec-5920-4fc1-8886-6a70a324837d","name":"Mistral 7B Instruct","model_id":"mistral-7b-instruct::default","variant":null,"harness":null},"value":-64.9166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 217b34ec-5920-4fc1-8886-6a70a324837d; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:219ed587-60c5-4a48-9517-8480e08d0ca1:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"219ed587-60c5-4a48-9517-8480e08d0ca1","name":"Gemini 2.5 Flash (Reasoning)","model_id":"gemini-2.5-flash-preview-04-17-thinking::reasoning","variant":null,"harness":null},"value":-29.8,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 219ed587-60c5-4a48-9517-8480e08d0ca1; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:21a0a2f6-bc72-40d2-80db-ea4e66b02b90:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"21a0a2f6-bc72-40d2-80db-ea4e66b02b90","name":"GPT-6 Astra (Non-reasoning)","model_id":null,"variant":null,"harness":null},"value":26.55,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 21a0a2f6-bc72-40d2-80db-ea4e66b02b90; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:222fb320-6e55-4672-846a-b6d5a24a45f4:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"222fb320-6e55-4672-846a-b6d5a24a45f4","name":"Gemma 3 4B Instruct","model_id":"gemma-3-4b-instruct::default","variant":null,"harness":null},"value":-82.8833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 222fb320-6e55-4672-846a-b6d5a24a45f4; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:2236df45-0699-40d1-b5cc-69ee345d2257:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2236df45-0699-40d1-b5cc-69ee345d2257","name":"Qwen3.5 122B A10B (Reasoning)","model_id":"qwen3.5-122b-a10b::reasoning","variant":null,"harness":null},"value":-41.5,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2236df45-0699-40d1-b5cc-69ee345d2257; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:22d09131-343b-4adf-8760-533e20a2155f:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"22d09131-343b-4adf-8760-533e20a2155f","name":"MiMo-V2.5","model_id":"mimo-v2.5::default","variant":null,"harness":null},"value":-9.83333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 22d09131-343b-4adf-8760-533e20a2155f; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:23149f9b-c904-43e2-9ec4-afa2bf843941:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"23149f9b-c904-43e2-9ec4-afa2bf843941","name":"Grok 4.1 Fast (Reasoning)","model_id":"grok-4.1-fast::reasoning","variant":null,"harness":null},"value":-29.9166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 23149f9b-c904-43e2-9ec4-afa2bf843941; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:235060f4-057d-4bd1-8b8e-4a92908c770e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"235060f4-057d-4bd1-8b8e-4a92908c770e","name":"Hermes 4 - Llama-3.1 70B (Non-reasoning)","model_id":"hermes-4-llama-3.1-70b::non-reasoning","variant":null,"harness":null},"value":-48.5833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 235060f4-057d-4bd1-8b8e-4a92908c770e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:23b379f7-18df-492a-9fc1-a56c5a5b9cfc:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"23b379f7-18df-492a-9fc1-a56c5a5b9cfc","name":"NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)","model_id":"nemotron-3-nano-30b-a3b::non-reasoning","variant":null,"harness":null},"value":-69.3,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 23b379f7-18df-492a-9fc1-a56c5a5b9cfc; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:23c86e4a-c769-43c0-a056-79e3cd15834f:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"23c86e4a-c769-43c0-a056-79e3cd15834f","name":"Claude Sonnet 5 (Adaptive Reasoning, Max Effort)","model_id":"claude-sonnet-5::max","variant":"max","harness":null},"value":16.45,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 23c86e4a-c769-43c0-a056-79e3cd15834f; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort max","comparison_key":null},{"id":"aa:2443ac9e-a3db-423d-accb-8963f6fb0a53:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2443ac9e-a3db-423d-accb-8963f6fb0a53","name":"Grok 3","model_id":"grok-3::default","variant":null,"harness":null},"value":-33.1833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2443ac9e-a3db-423d-accb-8963f6fb0a53; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:248deb0d-426c-4fa9-86fa-bc60aa9c3719:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"248deb0d-426c-4fa9-86fa-bc60aa9c3719","name":"GLM 5V Turbo (Reasoning)","model_id":"glm-5v-turbo::reasoning","variant":null,"harness":null},"value":-19.2833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 248deb0d-426c-4fa9-86fa-bc60aa9c3719; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:24ac5b00-5f03-4c47-8e37-522d1195383e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"24ac5b00-5f03-4c47-8e37-522d1195383e","name":"Mistral Small 3.1","model_id":"mistral-small-3.1-24b-instruct::default","variant":null,"harness":null},"value":-50.75,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 24ac5b00-5f03-4c47-8e37-522d1195383e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:2660d74f-ce79-48a8-8b53-6e668e2071a2:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2660d74f-ce79-48a8-8b53-6e668e2071a2","name":"Claude Opus 4.5 (Reasoning)","model_id":"claude-opus-4.5::reasoning","variant":null,"harness":null},"value":14,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2660d74f-ce79-48a8-8b53-6e668e2071a2; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:26614164-6840-4e17-a65a-2deb2fe7e87b:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"26614164-6840-4e17-a65a-2deb2fe7e87b","name":"Grok 4.6 (medium)","model_id":"grok-4.6::medium","variant":"medium","harness":null},"value":28,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 26614164-6840-4e17-a65a-2deb2fe7e87b; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort medium","comparison_key":null},{"id":"aa:2698f6c6-e436-47ce-a583-dbc25596c571:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2698f6c6-e436-47ce-a583-dbc25596c571","name":"Qwen3 Next 80B A3B Instruct","model_id":"qwen3-next-80b-a3b-instruct::default","variant":null,"harness":null},"value":-59.5,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2698f6c6-e436-47ce-a583-dbc25596c571; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:26c0b5df-efa7-470f-a65e-2d883329e493:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"26c0b5df-efa7-470f-a65e-2d883329e493","name":"Llama Nemotron Super 49B v1.5 (Non-reasoning)","model_id":"llama-nemotron-super-49b-v1.5::non-reasoning","variant":null,"harness":null},"value":-46.1833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 26c0b5df-efa7-470f-a65e-2d883329e493; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:26e0f83a-ca98-4f34-94ac-7c5e251ee410:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"26e0f83a-ca98-4f34-94ac-7c5e251ee410","name":"GPT-5.6 Terra (medium)","model_id":"gpt-5.6-terra::medium","variant":"medium","harness":null},"value":-5.13333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 26e0f83a-ca98-4f34-94ac-7c5e251ee410; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort medium","comparison_key":null},{"id":"aa:27202e5f-c82d-4710-92e9-4317877d4883:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"27202e5f-c82d-4710-92e9-4317877d4883","name":"Gemini 2.5 Pro","model_id":"gemini-2.5-pro::default","variant":null,"harness":null},"value":-16.35,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 27202e5f-c82d-4710-92e9-4317877d4883; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:272ff333-442f-4169-a804-ac9177bc99d7:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"272ff333-442f-4169-a804-ac9177bc99d7","name":"MiniMax-M2.1","model_id":"minimax-m2.1::default","variant":null,"harness":null},"value":-32.8666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 272ff333-442f-4169-a804-ac9177bc99d7; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:277f939a-985b-4b37-859d-b3eabc7c0b26:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"277f939a-985b-4b37-859d-b3eabc7c0b26","name":"MiniMax-M3","model_id":"minimax-m3::default","variant":null,"harness":null},"value":1.35,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 277f939a-985b-4b37-859d-b3eabc7c0b26; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:296ace9b-0815-43b2-bafa-fd6cec5cce36:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"296ace9b-0815-43b2-bafa-fd6cec5cce36","name":"MiMo-V2-Omni-0327","model_id":"mimo-v2-omni-0327::default","variant":null,"harness":null},"value":-15.1,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 296ace9b-0815-43b2-bafa-fd6cec5cce36; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:29855680-7469-43eb-8b88-cd3fb1d99da3:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"29855680-7469-43eb-8b88-cd3fb1d99da3","name":"GPT-5 mini (high)","model_id":"gpt-5-mini::high","variant":"high","harness":null},"value":-17.3166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 29855680-7469-43eb-8b88-cd3fb1d99da3; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort high","comparison_key":null},{"id":"aa:29976311-665a-4b2f-ac72-557c33e0758e:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"29976311-665a-4b2f-ac72-557c33e0758e","name":"Nemotron 3.5 Lightning","model_id":"nemotron-3.5-lightning::default","variant":null,"harness":null},"value":-17.7166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 29976311-665a-4b2f-ac72-557c33e0758e; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:2aacdc07-5f4e-4ab9-8ea5-5f7ab93f9eeb:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2aacdc07-5f4e-4ab9-8ea5-5f7ab93f9eeb","name":"Qwen3 4B 2507 (Reasoning)","model_id":"qwen3-4b-2507::reasoning","variant":null,"harness":null},"value":-60.2666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2aacdc07-5f4e-4ab9-8ea5-5f7ab93f9eeb; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:2bb84433-f38e-4edc-9b65-4d7b1f473db9:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2bb84433-f38e-4edc-9b65-4d7b1f473db9","name":"Qwen3 1.7B (Non-reasoning)","model_id":"qwen3-1.7b::non-reasoning","variant":null,"harness":null},"value":-84.0833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2bb84433-f38e-4edc-9b65-4d7b1f473db9; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:2bfdd17a-e027-4068-a54e-b0e90a6df118:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2bfdd17a-e027-4068-a54e-b0e90a6df118","name":"Gemma 3 27B Instruct","model_id":"gemma-3-27b-instruct::default","variant":null,"harness":null},"value":-67.2166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2bfdd17a-e027-4068-a54e-b0e90a6df118; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:2c4394a2-b443-470a-908e-5c4a271b780c:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2c4394a2-b443-470a-908e-5c4a271b780c","name":"GLM-4.7-Flash (Reasoning)","model_id":"glm-4.7-flash::reasoning","variant":null,"harness":null},"value":-62.6166666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2c4394a2-b443-470a-908e-5c4a271b780c; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:2cff73da-4855-403c-afc9-5540feadcc15:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2cff73da-4855-403c-afc9-5540feadcc15","name":"Granite 3.3 8B (Non-reasoning)","model_id":"granite-3.3-8b::non-reasoning","variant":null,"harness":null},"value":-77.2833333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2cff73da-4855-403c-afc9-5540feadcc15; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:2d28a13a-096e-475a-beb8-26bbd1c7d51c:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2d28a13a-096e-475a-beb8-26bbd1c7d51c","name":"Qwen3.5 9B (Reasoning)","model_id":"qwen3.5-9b::reasoning","variant":null,"harness":null},"value":-53.4666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2d28a13a-096e-475a-beb8-26bbd1c7d51c; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null},{"id":"aa:2dbb6dc7-8c40-4b6d-af9c-cf805f83b79a:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2dbb6dc7-8c40-4b6d-af9c-cf805f83b79a","name":"Grok 4 Fast (Non-reasoning)","model_id":"grok-4-fast::non-reasoning","variant":null,"harness":null},"value":-54.4333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-5-6-sol","retrieved_at":"2026-09-10T21:47:16.627Z","published_at":null,"sha256":"d921f7b255347b1091c5595adbbb5170ed6e9fe62250967a8586eb303ee99d2d","file":"ops/rebuild-2026-09/evidence/phase-04/sources/aa-29d2fef1679c.html.gz","locator":"model UUID 2dbb6dc7-8c40-4b6d-af9c-cf805f83b79a; omniscience"},"protocol":"Headline Omniscience Index: rewards correct answers, penalizes incorrect guesses, neutral abstentions; AA methodology captured 2026-09-22; effort not in effort field (exact UUID retained)","comparison_key":null}],"divergences":[],"cell":null,"coverage":{"model":null,"benchmark":{"total_models":890,"available":535,"unknown":355,"not_tested":0,"not_published":0,"source_unreachable":0,"contested":0,"measured":535,"self_reported":0,"observations":538,"unmatched_observations":3}},"collection":{"benchmark_id":"aa-omniscience::snapshot-2026-09-10","status":"collected","source_url":"https://artificialanalysis.ai/models/gpt-5-6-sol","reason":"Exact AA UUID and field from the reviewed protocol snapshot; null does not prove whether AA ran the test."},"coverage_note":"Denominators are catalog model configurations × versioned registry entries; capability_available excludes Efficiency (cost) boards. Basis counts count covered cells, not runs; measured and self_reported may overlap. Unmatched source identities remain in observations and never inflate catalog coverage."}