{"rewrite":{"id":"r_1b1a4fce6c1c9c44b90eb562","clusterId":"c_f8467e926ad72b0c1385947e","slug":"openai-launches-genebench-pro-to-measure-ai-scientific-reasoning","model":"deepseek-v4-flash","headline":"OpenAI Launches GeneBench-Pro to Measure AI Scientific Reasoning","summary":"OpenAI announced GeneBench-Pro, a computational biology benchmark that tests whether AI can judge if data is noise or significant, handle ambiguity, and perform iterative analysis. Its top model, GPT-5.6 Sol, scored 31.5% at the highest reasoning setting, while human experts estimate each problem takes 20 to 40 hours. OpenAI says partial automation could already generate scientific value.","whyItMatters":"The benchmark targets the gap between AI that can follow workflows and AI that can make the high-level judgments real scientific research requires, with current models solving less than a third of problems.","webCardHtml":"\u003cp\u003eOpenAI released GeneBench-Pro, a benchmark designed to test whether AI can do more than recall facts or follow predefined steps. Each problem presents unorganized datasets and experimental backgrounds, requiring the AI to explore data, select analysis methods, and iterate toward an answer. OpenAI notes that scientific data rarely comes with a manual, and researchers must judge whether a pattern reflects a real phenomenon or is noise.\u003c/p\u003e\u003cp\u003eWhen tested, OpenAI\u0026#39;s most powerful model GPT-5.6 Sol achieved a pass rate of 31.5% at the top reasoning setting. At the lowest reasoning level, the pass rate stayed in single digits, showing a sixfold increase with more computation. OpenAI stated that if progress continues at the current pace, the benchmark could be saturated by the end of the year.\u003c/p\u003e","blueskyPost":"OpenAI announced GeneBench-Pro, a computational biology benchmark for AI scientific reasoning. Its top model scored 31.5%. Human experts estimate each problem takes 20-40 hours. OpenAI says partial automation could already generate value.","twitterPost":"OpenAI announced GeneBench-Pro, a benchmark that tests whether AI can judge noise vs. significant data in scientific research. Top model GPT-5.6 Sol scored 31.5%. Human experts estimate each problem takes 20-40 hours.","threadsPost":null,"newsletterBlurb":"OpenAI announced GeneBench-Pro, a computational biology benchmark that measures whether AI can make high-level judgments like correcting assumptions and handling ambiguity in real scientific data. Its top model GPT-5.6 Sol scored 31.5% at the highest reasoning setting, while human experts estimate each problem takes 20 to 40 hours. OpenAI says partial automation could already generate significant economic and scientific value.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20260701-genebench-pro/\",\"title\":\"OpenAI Announces GeneBench-Pro, a Benchmark Test for Measuring AI's Scientific Ability\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":4208,"outputTokens":588,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1782878454,"createdAt":"2026-07-01T03:51:13.000Z","publishedAt":"2026-07-01T03:54:50.000Z","updatedAt":"2026-07-01T03:54:50.000Z"},"cluster":{"id":"c_f8467e926ad72b0c1385947e","canonicalTitle":"OpenAIがAIの科学能力を測定するベンチマークテスト「GeneBench-Pro」を発表","representativeArticleId":"a_16a103acac6485afcaf4bcf1","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[],\"studios\":[],\"people\":[],\"type\":\"news\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-07-01T03:05:00.000Z","lastSeenAt":"2026-07-01T03:05:00.000Z","updatedAt":"2026-07-01T03:54:51.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20260701-genebench-pro/","title":"OpenAIがAIの科学能力を測定するベンチマークテスト「GeneBench-Pro」を発表"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":[],"studios":[],"people":[],"type":"news","domain":"other","is_roundup":false},"keyFacts":["OpenAI released GeneBench-Pro, a computational biology benchmark that tests whether AI can judge if data is noise or significant, handle ambiguity, and perform iterative analysis.","OpenAI's top model, GPT-5.6 Sol, scored 31.5% at the highest reasoning setting on GeneBench-Pro.","Human experts estimate each GeneBench-Pro problem takes 20 to 40 hours to solve.","At the lowest reasoning level, GPT-5.6 Sol's pass rate on GeneBench-Pro stayed in single digits, showing a sixfold increase with more computation.","OpenAI stated that if progress continues at the current pace, GeneBench-Pro could be saturated by the end of the year."]}