AInsteinBench - Cheminformatics: leaderboard

The AInsteinBench problems from RDKit only (the paper's CI column; the subset size is shown only in a figure), solved by the model in the CodeAct agent; the score is the share resolved. ByteDance Seed, which also makes Doubao-Seed-1.8, wrote the benchmark and ran every model.

Metric: % Resolved. Source: arxiv.org. Saturation forecast: Around October 2027. 7 models tracked. Updated 17 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3 Pro (Preview)19.6#120
2Claude Opus 4.519.6#161
3Seed 1.817.4#250
4Claude Sonnet 4.515.2#258
5GPT-5.110.9#235
6GPT-5High8.7#177
7GLM-4.60#496

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=ainsteinbench-cheminformatics · How It Works · Data refreshed daily, snapshot 2026-11-17.