{"type":"post","id":"openai-releases-biobasicsbench-for-ai-agents-on-wet-2ea06d","slug":"openai-releases-biobasicsbench-for-ai-agents-on-wet-2ea06d","title":"OpenAI releases BioBasicsBench for AI agents on wet-lab analysis","description":"OpenAI and biotech company Ligo have published BioBasicsBench, a 100-task benchmark for testing AI agents on evidence from everyday wet-lab work.","retrieval_nugget":"OpenAI and biotech company Ligo have published BioBasicsBench, a 100-task benchmark for testing AI agents on evidence from everyday wet-lab work. Its tasks emphasize interpreting raw experimental materials, catching errors, and declining unsupported conclusions; the reported model scores offer a concrete comparison, while the benchmark’s failure cases show how much careful verification still matters.","published_at":"2026-11-06","updated_at":"2026-11-06","record_date":"2026-11-06","date_kind":"published_at","topics":["evals"],"entities":["OpenAI","Ligo","BioBasicsBench","GPT-6 Astra","GPT-5.6 Sol","GPT-6.1 Sol","GPT-6 Luna"],"related_patterns":["scientific-agents-need-artifact-evidence"],"novelty_label":"new_fact","what_changed":"OpenAI and Ligo introduce BioBasicsBench, a 100-task benchmark that evaluates agents on messy wet-lab evidence and reports model scores and failure modes.","prior_refs":["https://newruntime.com/posts/openai-releases-gpt-6-rosalind-for-biological-reasoning-325c40/"],"source_url":"https://openai.com/index/measuring-how-ai-agents-handle-wet-lab-science","source_urls":["https://openai.com/index/measuring-how-ai-agents-handle-wet-lab-science"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:openai-releases-biobasicsbench-for-ai-agents-on-wet-2ea06d","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/openai-releases-biobasicsbench-for-ai-agents-on-wet-2ea06d/","markdown":"https://newruntime.com/posts/openai-releases-biobasicsbench-for-ai-agents-on-wet-2ea06d.md","json":"https://newruntime.com/posts/openai-releases-biobasicsbench-for-ai-agents-on-wet-2ea06d.json"},"markdown_url":"https://newruntime.com/posts/openai-releases-biobasicsbench-for-ai-agents-on-wet-2ea06d.md","next_reads":[{"type":"topic","path":"/topics/evals/","url":"https://newruntime.com/topics/evals/","title":"Evals","reason":"Explore the evals topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/evals.md","json_url":"https://newruntime.com/topics/evals.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}