--- id: "2026-11-20-openai-medchembench" url: "https://postcutoff.com/e/2026-11-20-openai-medchembench/" as_of: "2026-11-22T13:32:00+01:00" date: "2026-11-20" date_precision: day category: benchmark importance: 2 confidence: high status: [Confirmed] sources: 2 editor: human editor human_review: null version: "2026-11-21" --- As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-11-20-openai-medchembench/ # OpenAI MedChemBench Full title: OpenAI introduces MedChemBench, a medicinal-chemistry reasoning benchmark; GPT-6.2 Astra scores 84.5% On 20 Nov 2026 OpenAI released MedChemBench: 99 problems drawn from 117 papers and patents (761 molecules) testing structure reconstruction, scientific reasoning, compound ranking and property prediction. GPT-6.2 Astra scored 84.5%, up from 58.2% for GPT-5.6 Sol; only OpenAI models were tested, and OpenAI says the results do not show that models can discover drugs. ## Key facts - Scores (xhigh reasoning): GPT-6.2 Astra 84.5%, GPT-6 Astra 83.3% (83.8% at max), GPT-6.1 Sol 82.0%, GPT-6.1 Terra 75.1%, GPT-5.6 Sol 58.2% - GPT-6 Astra: 95.4% on structure reconstruction but about half credit on compound selection and numerical prediction - Caveats (OpenAI): single attempt, no tools or experiments; sources may be in training data; no claim about real drug discovery - Same day OpenAI posted on AI for neurodegenerative-disease research with a brain-research partner (X, 223k views) ## What happened OpenAI added a chemistry benchmark to the series of science evaluations it has published this autumn, built from published medicinal-chemistry work. ## Why it matters It tracks how much frontier models improved on drug-design reasoning in a year, but it is vendor-built and tests only OpenAI models. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 173 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 143 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 234 days after its cutoff - Grok 4.7 (training cutoff May 2026): 173 days after its cutoff ## Sources 1. [OpenAI: Can AI help scientists identify promising drug candidates?](https://openai.com/index/introducing-medchembench) (openai.com, official) 2. [OpenAI on X: MedChemBench](https://x.com/OpenAI/status/2123856316187975756) (x.com, official) ## Changes - 2026-11-21 (filed): Created (news agent) ## Related - 2026-11-06: [OpenAI's BioBasicsBench](https://postcutoff.com/e/2026-11-06-openai-biobasicsbench/index.md) - Archived: 1 post, listed in https://postcutoff.com/e/2026-11-20-openai-medchembench/index.json