{"schema_version":1,"total":538,"offset":500,"limit":100,"observations":[{"id":"aa:f5d83128-047f-496d-ba49-8a428abe8345:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"f5d83128-047f-496d-ba49-8a428abe8345","name":"Qwen3 VL 4B Instruct","model_id":"qwen3-vl-4b-instruct::default","variant":null,"harness":null},"value":-75.9666666666667,"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 f5d83128-047f-496d-ba49-8a428abe8345; 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:f6ccbe1d-bd7e-484b-9795-18cc9f91552d:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"f6ccbe1d-bd7e-484b-9795-18cc9f91552d","name":"Qwen3 235B A22B 2507 (Reasoning)","model_id":"qwen3-235b-a22b-thinking-2507::reasoning","variant":null,"harness":null},"value":-46.5166666666667,"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 f6ccbe1d-bd7e-484b-9795-18cc9f91552d; 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:f6db039b-0f3b-485c-9d7f-982988e44f26:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"f6db039b-0f3b-485c-9d7f-982988e44f26","name":"Gemini 3.8 Flash (low)","model_id":"gemini-3.8-flash::low","variant":"low","harness":null},"value":21.35,"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 f6db039b-0f3b-485c-9d7f-982988e44f26; 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:f74ea286-cd29-4eb4-af14-1389b19c21e5:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"f74ea286-cd29-4eb4-af14-1389b19c21e5","name":"MiniMax-M2","model_id":"minimax-m2::default","variant":null,"harness":null},"value":-46.55,"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 f74ea286-cd29-4eb4-af14-1389b19c21e5; 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:f78138d6-2e04-4a84-919a-20d177cb6ff1:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"f78138d6-2e04-4a84-919a-20d177cb6ff1","name":"Jamba Reasoning 3B","model_id":"jamba-reasoning-3b::default","variant":null,"harness":null},"value":-57.7166666666667,"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 f78138d6-2e04-4a84-919a-20d177cb6ff1; 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:f7a4ea75-e548-4069-80d4-9be8bc7c009b:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"f7a4ea75-e548-4069-80d4-9be8bc7c009b","name":"GLM-5.2 (max)","model_id":"glm-5.2::max","variant":"max","harness":null},"value":4.43333333333333,"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 f7a4ea75-e548-4069-80d4-9be8bc7c009b; 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:f7d2fc3e-1f7b-405f-818c-07952a4af78f:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"f7d2fc3e-1f7b-405f-818c-07952a4af78f","name":"Kimi K3 (max)","model_id":"kimi-k3::max","variant":"max","harness":null},"value":19.7,"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 f7d2fc3e-1f7b-405f-818c-07952a4af78f; 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:f93d0750-b659-4ceb-a123-7e657904ef2b:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"f93d0750-b659-4ceb-a123-7e657904ef2b","name":"Qwen3 VL 4B (Reasoning)","model_id":"qwen3-vl-4b::reasoning","variant":null,"harness":null},"value":-68.3833333333333,"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 f93d0750-b659-4ceb-a123-7e657904ef2b; 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:f9739750-6d42-450f-ba1e-2f76c869b4fe:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"f9739750-6d42-450f-ba1e-2f76c869b4fe","name":"Quasar 438B (max, based on GLM-5.2)","model_id":"quasar-438b::max","variant":null,"harness":null},"value":-2.6,"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 f9739750-6d42-450f-ba1e-2f76c869b4fe; 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:fb112343-c82c-4b43-afea-996bd5101d62:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"fb112343-c82c-4b43-afea-996bd5101d62","name":"KAT-Coder-Pro V1","model_id":"kat-coder-pro-v1::default","variant":null,"harness":null},"value":-37.7333333333333,"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 fb112343-c82c-4b43-afea-996bd5101d62; 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:fb65266f-5a7d-403c-85d5-ccdf0d1ca838:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"fb65266f-5a7d-403c-85d5-ccdf0d1ca838","name":"DeepSeek V3.1 (Non-reasoning)","model_id":"deepseek-v3.1::non-reasoning","variant":null,"harness":null},"value":-42.75,"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 fb65266f-5a7d-403c-85d5-ccdf0d1ca838; 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:fbc58677-e324-4b45-a979-7fd8eec555cd:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"fbc58677-e324-4b45-a979-7fd8eec555cd","name":"LFM2 24B A2B","model_id":"lfm2-24b-a2b::default","variant":null,"harness":null},"value":-58.1,"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 fbc58677-e324-4b45-a979-7fd8eec555cd; 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:fbdf8da1-b341-448c-b3cb-8aff1d8f70b9:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"fbdf8da1-b341-448c-b3cb-8aff1d8f70b9","name":"Nova 2.0 Lite (medium)","model_id":"nova-2.0-lite::medium","variant":"medium","harness":null},"value":-56.9666666666667,"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 fbdf8da1-b341-448c-b3cb-8aff1d8f70b9; 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:fc4223e8-4586-4ca1-97ca-bb55ff586947:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"fc4223e8-4586-4ca1-97ca-bb55ff586947","name":"KAT Coder Pro V2","model_id":"kat-coder-pro-v2::default","variant":null,"harness":null},"value":-22.4666666666667,"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 fc4223e8-4586-4ca1-97ca-bb55ff586947; 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:fc92f822-04b7-420d-9c07-a21af5e9aac7:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"fc92f822-04b7-420d-9c07-a21af5e9aac7","name":"Qwen3 Coder Next","model_id":"qwen3-coder-next::default","variant":null,"harness":null},"value":-62.4,"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 fc92f822-04b7-420d-9c07-a21af5e9aac7; 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:fd4454ff-e703-46c0-a7f5-fa69af09486d:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"fd4454ff-e703-46c0-a7f5-fa69af09486d","name":"GPT-5.1 Codex mini (high)","model_id":"gpt-5.1-codex-mini::high","variant":"high","harness":null},"value":-16.4166666666667,"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 fd4454ff-e703-46c0-a7f5-fa69af09486d; 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:fe2c2289-d261-4433-8681-46448372c1f6:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"fe2c2289-d261-4433-8681-46448372c1f6","name":"Grok 4.3 (low)","model_id":"grok-4.3::low","variant":"low","harness":null},"value":13.9333333333333,"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 fe2c2289-d261-4433-8681-46448372c1f6; 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:fe4c0848-e284-4e52-a79d-cdc28392f1a9:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"fe4c0848-e284-4e52-a79d-cdc28392f1a9","name":"DeepSeek V4 Flash 0731 (Reasoning, Max Effort)","model_id":"deepseek-v4-flash-0731::max","variant":"max","harness":null},"value":-14.2833333333333,"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 fe4c0848-e284-4e52-a79d-cdc28392f1a9; 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:feb02d3b-ff8d-4ed4-b165-13f8d4a7192c:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"feb02d3b-ff8d-4ed4-b165-13f8d4a7192c","name":"Gemma 4 12B (Reasoning)","model_id":"gemma-4-12b::reasoning","variant":null,"harness":null},"value":-52.7166666666667,"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 feb02d3b-ff8d-4ed4-b165-13f8d4a7192c; 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:ff51be8f-e362-4a7e-9043-687ba15de207:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"ff51be8f-e362-4a7e-9043-687ba15de207","name":"Claude Opus 5 (Adaptive Reasoning, Medium Effort)","model_id":"claude-opus-5::medium","variant":"medium","harness":null},"value":31.0166666666667,"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 ff51be8f-e362-4a7e-9043-687ba15de207; 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:ff9bc5e5-a02f-4270-983e-4b3f834f3363:omniscience","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"ff9bc5e5-a02f-4270-983e-4b3f834f3363","name":"Grok 3 mini Reasoning (high)","model_id":"grok-3-mini-reasoning::high","variant":"high","harness":null},"value":-6.8,"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 ff9bc5e5-a02f-4270-983e-4b3f834f3363; 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":"cr128:ea91cd145268cb2d3e434c2c","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"2f3c4dc9-a450-4303-8697-0237257cf08f","name":"Claude Opus 5.5 (max with fallback) [claude-opus-5-5]","model_id":"claude-opus-5.5::max","variant":"max","harness":null},"value":46.416666666666664,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/claude-opus-5-5","retrieved_at":"2026-09-22T22:47:41.526299+00:00","published_at":null,"sha256":"d8fae69000dc9c763a16b987995f00530de80a84ed1a0ea92cd4750efc45ccbf","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/d8fae69000dc9c763a16.gz","locator":"AA-Omniscience; Claude Opus 5.5 (max with fallback) [claude-opus-5-5]; exact source excerpt: \"omniscience\":46.416666666666664 (page payload, model slug claude-opus-5-5)"},"protocol":"AA-Omniscience; source configuration Claude Opus 5.5 (max with fallback) [claude-opus-5-5]; page date retrieved 2026-09-22 (model release 2026-09-22); AA labels this variant Default Fallback. source row: {\"model\":\"Claude Opus 5.5\",\"config\":\"Claude Opus 5.5 (max with fallback) [claude-opus-5-5]\",\"source_quote\":\"\\\"omniscience\\\":46.416666666666664 (page payload, model slug claude-opus-5-5)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":46.42}","comparison_key":null},{"id":"cr128:2b0008760bc37ccd53a5c9e9","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"f314eade-2232-44bf-a3ab-9b326bc67de6","name":"Claude Opus 5.5 (high with fallback) [claude-opus-5-5-high]","model_id":"claude-opus-5.5::high","variant":"high","harness":null},"value":40.63333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/claude-opus-5-5","retrieved_at":"2026-09-22T22:47:41.526299+00:00","published_at":null,"sha256":"d8fae69000dc9c763a16b987995f00530de80a84ed1a0ea92cd4750efc45ccbf","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/d8fae69000dc9c763a16.gz","locator":"AA-Omniscience; Claude Opus 5.5 (high with fallback) [claude-opus-5-5-high]; exact source excerpt: \"omniscience\":40.63333333333333 (page payload, model slug claude-opus-5-5-high)"},"protocol":"AA-Omniscience; source configuration Claude Opus 5.5 (high with fallback) [claude-opus-5-5-high]; page date retrieved 2026-09-22 (model release 2026-09-17); AA labels this variant Default Fallback. source row: {\"model\":\"Claude Opus 5.5\",\"config\":\"Claude Opus 5.5 (high with fallback) [claude-opus-5-5-high]\",\"source_quote\":\"\\\"omniscience\\\":40.63333333333333 (page payload, model slug claude-opus-5-5-high)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":40.63}","comparison_key":null},{"id":"cr128:1541019fa6dea380d7a610aa","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"4416ca93-fde6-4b7b-abbc-3a6be109cc3d","name":"Claude Opus 5.5 (low with fallback) [claude-opus-5-5-low]","model_id":"claude-opus-5.5::low","variant":"low","harness":null},"value":38.86666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/claude-opus-5-5","retrieved_at":"2026-09-22T22:47:41.526299+00:00","published_at":null,"sha256":"d8fae69000dc9c763a16b987995f00530de80a84ed1a0ea92cd4750efc45ccbf","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/d8fae69000dc9c763a16.gz","locator":"AA-Omniscience; Claude Opus 5.5 (low with fallback) [claude-opus-5-5-low]; exact source excerpt: \"omniscience\":38.86666666666667 (page payload, model slug claude-opus-5-5-low)"},"protocol":"AA-Omniscience; source configuration Claude Opus 5.5 (low with fallback) [claude-opus-5-5-low]; page date retrieved 2026-09-22 (model release 2026-09-17); AA labels this variant Default Fallback. source row: {\"model\":\"Claude Opus 5.5\",\"config\":\"Claude Opus 5.5 (low with fallback) [claude-opus-5-5-low]\",\"source_quote\":\"\\\"omniscience\\\":38.86666666666667 (page payload, model slug claude-opus-5-5-low)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":38.87}","comparison_key":null},{"id":"cr128:5c16b4222ae43ecefa14712a","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"ea9e0da6-169f-43c6-92f5-730a10d6ff8d","name":"Claude Opus 5.5 (medium with fallback) [claude-opus-5-5-medium]","model_id":"claude-opus-5.5::medium","variant":"medium","harness":null},"value":40.31666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/claude-opus-5-5","retrieved_at":"2026-09-22T22:47:41.526299+00:00","published_at":null,"sha256":"d8fae69000dc9c763a16b987995f00530de80a84ed1a0ea92cd4750efc45ccbf","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/d8fae69000dc9c763a16.gz","locator":"AA-Omniscience; Claude Opus 5.5 (medium with fallback) [claude-opus-5-5-medium]; exact source excerpt: \"omniscience\":40.31666666666667 (page payload, model slug claude-opus-5-5-medium)"},"protocol":"AA-Omniscience; source configuration Claude Opus 5.5 (medium with fallback) [claude-opus-5-5-medium]; page date retrieved 2026-09-22 (model release 2026-09-17); AA labels this variant Default Fallback. source row: {\"model\":\"Claude Opus 5.5\",\"config\":\"Claude Opus 5.5 (medium with fallback) [claude-opus-5-5-medium]\",\"source_quote\":\"\\\"omniscience\\\":40.31666666666667 (page payload, model slug claude-opus-5-5-medium)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":40.32}","comparison_key":null},{"id":"cr128:dc5ff03643e0db9f6508b71a","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"df5bf99d-d228-4715-b41b-19ca86118777","name":"Claude Opus 5.5 (xhigh with fallback) [claude-opus-5-5-xhigh]","model_id":"claude-opus-5.5::xhigh","variant":"xhigh","harness":null},"value":42.65,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/claude-opus-5-5","retrieved_at":"2026-09-22T22:47:41.526299+00:00","published_at":null,"sha256":"d8fae69000dc9c763a16b987995f00530de80a84ed1a0ea92cd4750efc45ccbf","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/d8fae69000dc9c763a16.gz","locator":"AA-Omniscience; Claude Opus 5.5 (xhigh with fallback) [claude-opus-5-5-xhigh]; exact source excerpt: \"omniscience\":42.65 (page payload, model slug claude-opus-5-5-xhigh)"},"protocol":"AA-Omniscience; source configuration Claude Opus 5.5 (xhigh with fallback) [claude-opus-5-5-xhigh]; page date retrieved 2026-09-22 (model release 2026-09-17); AA labels this variant Default Fallback. source row: {\"model\":\"Claude Opus 5.5\",\"config\":\"Claude Opus 5.5 (xhigh with fallback) [claude-opus-5-5-xhigh]\",\"source_quote\":\"\\\"omniscience\\\":42.65 (page payload, model slug claude-opus-5-5-xhigh)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":42.65}","comparison_key":null},{"id":"cr128:7ffa3330c816f61e107e6904","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"c50ea08c-88c0-4eb7-85b8-27f2bbf6d527","name":"GPT-6 Sol (max) [gpt-6-sol]","model_id":"gpt-6-sol::max","variant":"max","harness":null},"value":27.116666666666667,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-sol","retrieved_at":"2026-09-22T22:47:42.063569+00:00","published_at":null,"sha256":"fb0216b316b19c56873d3e6e9e1636b625628a80542aea2e678a5fe9689ff28d","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/fb0216b316b19c56873d.gz","locator":"AA-Omniscience; GPT-6 Sol (max) [gpt-6-sol]; exact source excerpt: \"omniscience\":27.116666666666667 (page payload, model slug gpt-6-sol)"},"protocol":"AA-Omniscience; source configuration GPT-6 Sol (max) [gpt-6-sol]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Sol\",\"config\":\"GPT-6 Sol (max) [gpt-6-sol]\",\"source_quote\":\"\\\"omniscience\\\":27.116666666666667 (page payload, model slug gpt-6-sol)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":27.12}","comparison_key":null},{"id":"cr128:10debb679586d187feabf92e","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"52eebe3e-6ede-4e46-92db-c5dea49fc410","name":"GPT-6 Sol (high) [gpt-6-sol-high]","model_id":"gpt-6-sol::high","variant":"high","harness":null},"value":26.816666666666666,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-sol","retrieved_at":"2026-09-22T22:47:42.063569+00:00","published_at":null,"sha256":"fb0216b316b19c56873d3e6e9e1636b625628a80542aea2e678a5fe9689ff28d","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/fb0216b316b19c56873d.gz","locator":"AA-Omniscience; GPT-6 Sol (high) [gpt-6-sol-high]; exact source excerpt: \"omniscience\":26.816666666666666 (page payload, model slug gpt-6-sol-high)"},"protocol":"AA-Omniscience; source configuration GPT-6 Sol (high) [gpt-6-sol-high]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Sol\",\"config\":\"GPT-6 Sol (high) [gpt-6-sol-high]\",\"source_quote\":\"\\\"omniscience\\\":26.816666666666666 (page payload, model slug gpt-6-sol-high)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":26.82}","comparison_key":null},{"id":"cr128:bb5709079ca034ccef2adf7e","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"01459872-433a-4ab2-8e99-7083162172eb","name":"GPT-6 Sol (low) [gpt-6-sol-low]","model_id":"gpt-6-sol::low","variant":"low","harness":null},"value":26.516666666666666,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-sol","retrieved_at":"2026-09-22T22:47:42.063569+00:00","published_at":null,"sha256":"fb0216b316b19c56873d3e6e9e1636b625628a80542aea2e678a5fe9689ff28d","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/fb0216b316b19c56873d.gz","locator":"AA-Omniscience; GPT-6 Sol (low) [gpt-6-sol-low]; exact source excerpt: \"omniscience\":26.516666666666666 (page payload, model slug gpt-6-sol-low)"},"protocol":"AA-Omniscience; source configuration GPT-6 Sol (low) [gpt-6-sol-low]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Sol\",\"config\":\"GPT-6 Sol (low) [gpt-6-sol-low]\",\"source_quote\":\"\\\"omniscience\\\":26.516666666666666 (page payload, model slug gpt-6-sol-low)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":26.52}","comparison_key":null},{"id":"cr128:bec2c0d58df25b4e47415677","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"780a4a85-17ff-4175-a8dd-ebca4823e61b","name":"GPT-6 Sol (medium) [gpt-6-sol-medium]","model_id":"gpt-6-sol::medium","variant":"medium","harness":null},"value":27.016666666666666,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-sol","retrieved_at":"2026-09-22T22:47:42.063569+00:00","published_at":null,"sha256":"fb0216b316b19c56873d3e6e9e1636b625628a80542aea2e678a5fe9689ff28d","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/fb0216b316b19c56873d.gz","locator":"AA-Omniscience; GPT-6 Sol (medium) [gpt-6-sol-medium]; exact source excerpt: \"omniscience\":27.016666666666666 (page payload, model slug gpt-6-sol-medium)"},"protocol":"AA-Omniscience; source configuration GPT-6 Sol (medium) [gpt-6-sol-medium]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Sol\",\"config\":\"GPT-6 Sol (medium) [gpt-6-sol-medium]\",\"source_quote\":\"\\\"omniscience\\\":27.016666666666666 (page payload, model slug gpt-6-sol-medium)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":27.02}","comparison_key":null},{"id":"cr128:5caa697cdc85fe57f1c34305","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"d3e20e76-9e1a-45b6-b809-ad6aa37430cf","name":"GPT-6 Sol (Non-reasoning) [gpt-6-sol-non-reasoning]","model_id":"gpt-6-sol::non-reasoning","variant":"non-reasoning","harness":null},"value":-0.85,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-sol","retrieved_at":"2026-09-22T22:47:42.063569+00:00","published_at":null,"sha256":"fb0216b316b19c56873d3e6e9e1636b625628a80542aea2e678a5fe9689ff28d","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/fb0216b316b19c56873d.gz","locator":"AA-Omniscience; GPT-6 Sol (Non-reasoning) [gpt-6-sol-non-reasoning]; exact source excerpt: \"omniscience\":-0.85 (page payload, model slug gpt-6-sol-non-reasoning)"},"protocol":"AA-Omniscience; source configuration GPT-6 Sol (Non-reasoning) [gpt-6-sol-non-reasoning]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Sol\",\"config\":\"GPT-6 Sol (Non-reasoning) [gpt-6-sol-non-reasoning]\",\"source_quote\":\"\\\"omniscience\\\":-0.85 (page payload, model slug gpt-6-sol-non-reasoning)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":-0.85}","comparison_key":null},{"id":"cr128:de610c8417d4388ff679ac61","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"da2642fe-9f73-4788-b5af-24edcd55b37e","name":"GPT-6 Sol (xhigh) [gpt-6-sol-xhigh]","model_id":"gpt-6-sol::xhigh","variant":"xhigh","harness":null},"value":26.666666666666668,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-sol","retrieved_at":"2026-09-22T22:47:42.063569+00:00","published_at":null,"sha256":"fb0216b316b19c56873d3e6e9e1636b625628a80542aea2e678a5fe9689ff28d","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/fb0216b316b19c56873d.gz","locator":"AA-Omniscience; GPT-6 Sol (xhigh) [gpt-6-sol-xhigh]; exact source excerpt: \"omniscience\":26.666666666666668 (page payload, model slug gpt-6-sol-xhigh)"},"protocol":"AA-Omniscience; source configuration GPT-6 Sol (xhigh) [gpt-6-sol-xhigh]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Sol\",\"config\":\"GPT-6 Sol (xhigh) [gpt-6-sol-xhigh]\",\"source_quote\":\"\\\"omniscience\\\":26.666666666666668 (page payload, model slug gpt-6-sol-xhigh)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":26.67}","comparison_key":null},{"id":"cr128:423c6a8ede7cb612640167ea","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"6fb13851-40ce-4bda-ad3f-6b38e0c5daa7","name":"GPT-6 Luna (max) [gpt-6-luna]","model_id":"gpt-6-luna::max","variant":"max","harness":null},"value":0.65,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-luna","retrieved_at":"2026-09-22T22:47:42.324143+00:00","published_at":null,"sha256":"a9b2a3dc90eb3afb7cc51bc7a19fbaf7e317d5bf7bf9fed6a8182499511bf035","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/a9b2a3dc90eb3afb7cc5.gz","locator":"AA-Omniscience; GPT-6 Luna (max) [gpt-6-luna]; exact source excerpt: \"omniscience\":0.65 (page payload, model slug gpt-6-luna)"},"protocol":"AA-Omniscience; source configuration GPT-6 Luna (max) [gpt-6-luna]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Luna\",\"config\":\"GPT-6 Luna (max) [gpt-6-luna]\",\"source_quote\":\"\\\"omniscience\\\":0.65 (page payload, model slug gpt-6-luna)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":0.65}","comparison_key":null},{"id":"cr128:4f0e719f80724741d7031cdd","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"7d1229bc-deea-4717-ba5b-f59a35d991e3","name":"GPT-6 Luna (high) [gpt-6-luna-high]","model_id":"gpt-6-luna::high","variant":"high","harness":null},"value":-5.5,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-luna","retrieved_at":"2026-09-22T22:47:42.324143+00:00","published_at":null,"sha256":"a9b2a3dc90eb3afb7cc51bc7a19fbaf7e317d5bf7bf9fed6a8182499511bf035","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/a9b2a3dc90eb3afb7cc5.gz","locator":"AA-Omniscience; GPT-6 Luna (high) [gpt-6-luna-high]; exact source excerpt: \"omniscience\":-5.5 (page payload, model slug gpt-6-luna-high)"},"protocol":"AA-Omniscience; source configuration GPT-6 Luna (high) [gpt-6-luna-high]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Luna\",\"config\":\"GPT-6 Luna (high) [gpt-6-luna-high]\",\"source_quote\":\"\\\"omniscience\\\":-5.5 (page payload, model slug gpt-6-luna-high)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":-5.5}","comparison_key":null},{"id":"cr128:0ffceed20fa3a2d832a72e1d","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"bf9708d8-933d-44f6-affa-b696a7a650c9","name":"GPT-6 Luna (low) [gpt-6-luna-low]","model_id":"gpt-6-luna::low","variant":"low","harness":null},"value":-9.166666666666666,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-luna","retrieved_at":"2026-09-22T22:47:42.324143+00:00","published_at":null,"sha256":"a9b2a3dc90eb3afb7cc51bc7a19fbaf7e317d5bf7bf9fed6a8182499511bf035","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/a9b2a3dc90eb3afb7cc5.gz","locator":"AA-Omniscience; GPT-6 Luna (low) [gpt-6-luna-low]; exact source excerpt: \"omniscience\":-9.166666666666666 (page payload, model slug gpt-6-luna-low)"},"protocol":"AA-Omniscience; source configuration GPT-6 Luna (low) [gpt-6-luna-low]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Luna\",\"config\":\"GPT-6 Luna (low) [gpt-6-luna-low]\",\"source_quote\":\"\\\"omniscience\\\":-9.166666666666666 (page payload, model slug gpt-6-luna-low)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":-9.17}","comparison_key":null},{"id":"cr128:056b5ebc3122efe4159ee2f5","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"36667da0-9222-4967-adbb-f7efa15ad213","name":"GPT-6 Luna (medium) [gpt-6-luna-medium]","model_id":"gpt-6-luna::medium","variant":"medium","harness":null},"value":-5.05,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-luna","retrieved_at":"2026-09-22T22:47:42.324143+00:00","published_at":null,"sha256":"a9b2a3dc90eb3afb7cc51bc7a19fbaf7e317d5bf7bf9fed6a8182499511bf035","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/a9b2a3dc90eb3afb7cc5.gz","locator":"AA-Omniscience; GPT-6 Luna (medium) [gpt-6-luna-medium]; exact source excerpt: \"omniscience\":-5.05 (page payload, model slug gpt-6-luna-medium)"},"protocol":"AA-Omniscience; source configuration GPT-6 Luna (medium) [gpt-6-luna-medium]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Luna\",\"config\":\"GPT-6 Luna (medium) [gpt-6-luna-medium]\",\"source_quote\":\"\\\"omniscience\\\":-5.05 (page payload, model slug gpt-6-luna-medium)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":-5.05}","comparison_key":null},{"id":"cr128:b6e98ffcc8aff84ca59d9188","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"63cb48ea-0b0c-4e07-8ded-6d28dec4fa28","name":"GPT-6 Luna (Non-reasoning) [gpt-6-luna-non-reasoning]","model_id":"gpt-6-luna::non-reasoning","variant":"non-reasoning","harness":null},"value":-21.9,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-luna","retrieved_at":"2026-09-22T22:47:42.324143+00:00","published_at":null,"sha256":"a9b2a3dc90eb3afb7cc51bc7a19fbaf7e317d5bf7bf9fed6a8182499511bf035","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/a9b2a3dc90eb3afb7cc5.gz","locator":"AA-Omniscience; GPT-6 Luna (Non-reasoning) [gpt-6-luna-non-reasoning]; exact source excerpt: \"omniscience\":-21.9 (page payload, model slug gpt-6-luna-non-reasoning)"},"protocol":"AA-Omniscience; source configuration GPT-6 Luna (Non-reasoning) [gpt-6-luna-non-reasoning]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Luna\",\"config\":\"GPT-6 Luna (Non-reasoning) [gpt-6-luna-non-reasoning]\",\"source_quote\":\"\\\"omniscience\\\":-21.9 (page payload, model slug gpt-6-luna-non-reasoning)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":-21.9}","comparison_key":null},{"id":"cr128:297c8f756bec210202e71b4f","benchmark_id":"aa-omniscience::snapshot-2026-09-10","subject":{"source_id":"19813eb2-460a-475c-af65-810bb8660fec","name":"GPT-6 Luna (xhigh) [gpt-6-luna-xhigh]","model_id":"gpt-6-luna::xhigh","variant":"xhigh","harness":null},"value":-1.8333333333333333,"unit":"points","basis":"measured","source":{"url":"https://artificialanalysis.ai/models/gpt-6-luna","retrieved_at":"2026-09-22T22:47:42.324143+00:00","published_at":null,"sha256":"a9b2a3dc90eb3afb7cc51bc7a19fbaf7e317d5bf7bf9fed6a8182499511bf035","file":"data/raw/benchmarks/daily-evidence/2026-09-22-cr128-third-party/a9b2a3dc90eb3afb7cc5.gz","locator":"AA-Omniscience; GPT-6 Luna (xhigh) [gpt-6-luna-xhigh]; exact source excerpt: \"omniscience\":-1.8333333333333333 (page payload, model slug gpt-6-luna-xhigh)"},"protocol":"AA-Omniscience; source configuration GPT-6 Luna (xhigh) [gpt-6-luna-xhigh]; page date retrieved 2026-09-22 (model release 2026-09-22); source row: {\"model\":\"GPT-6 Luna\",\"config\":\"GPT-6 Luna (xhigh) [gpt-6-luna-xhigh]\",\"source_quote\":\"\\\"omniscience\\\":-1.8333333333333333 (page payload, model slug gpt-6-luna-xhigh)\",\"source_unit\":\"index (-100..100)\",\"displayed_value\":-1.83}","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."}