OpenAI's MedChemBench shows GPT-6.1 models near-perfect on medicinal chemistry reasoning

gdb · x · 2026-11-21

OpenAI released MedChemBench, a benchmark measuring frontier models' reasoning for identifying promising drug candidates. Greg Brockman called the progress in medicinal chemistry "very strong".

The shared results chart (average credit % vs average output tokens) shows:

The generational gap on molecular structure tasks is stark — newer models score far higher with far fewer output tokens.

Related event: OpenAI Launches MedChemBench for AI Drug Chemistry Reasoning(4 posts)→

Original post →

More from Models

Models channel →