{"version":1,"type":"story","url":"https://digestai.news/story/openai-releases-biobasicsbench-benchmark-gpt6-astra-scores-66-7-on-wet","json":"https://digestai.news/story/openai-releases-biobasicsbench-benchmark-gpt6-astra-scores-66-7-on-wet.json","markdown":"https://digestai.news/story/openai-releases-biobasicsbench-benchmark-gpt6-astra-scores-66-7-on-wet.md","slug":"openai-releases-biobasicsbench-benchmark-gpt6-astra-scores-66-7-on-wet","headline":"OpenAI releases BioBasicsBench benchmark; GPT‑6 Astra scores 66.7% on wet‑lab tasks","summary":"OpenAI and biotech firm Ligo introduced BioBasicsBench, a new benchmark of 100 routine wet‑lab tasks that require AI agents to read raw experimental data such as gel images, colony plates, microscopy stacks and instrument readouts. The benchmark evaluates whether agents can interpret the evidence, spot errors and recognize when the data do not support a conclusion.\n\nSeven OpenAI models were tested across 37 reasoning‑effort settings, with five attempts per task for a total of 18,500 results. At the highest \"xhigh\" setting, GPT‑6 Astra achieved an average of 66.7% of the available credit, compared with 43.8% for GPT‑5.6 Sol, showing notable gains in multimodal reasoning, error detection and context awareness. The results highlight both progress and remaining gaps, such as occasional over‑interpretation and mis‑counting of colonies.\n\nThe authors argue that tracking performance on BioBasicsBench will help improve AI assistance for biological research, reduce time spent on troubleshooting, and inform biosafety considerations.","keyPoints":["BioBasicsBench benchmark contains 100 wet‑lab tasks across five experimental areas.","GPT‑6 Astra achieved 66.7% mean reward at xhigh setting, versus 43.8% for GPT‑5.6 Sol.","Evaluation covered seven models, 37 settings, 18,500 attempts, showing multimodal reasoning improvements."],"whyItMatters":"The benchmark quantifies AI agents’ ability to interpret raw lab data, a step toward reliable AI assistance in biology, potentially speeding research and improving biosafety.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["OpenAI","Ligo"],"models":["GPT‑5.2","GPT‑5.4","GPT‑5.5","GPT‑5.6 Sol","GPT‑6.1 Sol","GPT‑6 Luna"],"people":[]},"firstPublishedAt":"2026-11-06T00:00:00Z","updatedAt":"2026-11-06T00:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"OpenAI","title":"Measuring how AI agents handle everyday wet-lab science","url":"https://openai.com/index/measuring-how-ai-agents-handle-wet-lab-science","publishedAt":"2026-11-06T00:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"OpenAI releases BioBasicsBench benchmark; GPT‑6 Astra scores 66.7% on wet‑lab tasks\", 6 November 2026, https://digestai.news/story/openai-releases-biobasicsbench-benchmark-gpt6-astra-scores-66-7-on-wet","publisher":"Digest AI","title":"OpenAI releases BioBasicsBench benchmark; GPT‑6 Astra scores 66.7% on wet‑lab tasks","datePublished":"2026-11-06T00:00:00Z","url":"https://digestai.news/story/openai-releases-biobasicsbench-benchmark-gpt6-astra-scores-66-7-on-wet"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}