MolDesignBench - Molecule Optimization: leaderboard
Metric: Success rate (%; share of the 1,000 optimization instances handled correctly: a valid SMILES satisfying every implicit and explicit property and functional-group constraint on the 900 feasible instances, staying similar to the given starting molecule, or an explicit None on the 100 infeasible ones; agent with the 17-tool chemistry toolset through function calling, at most 20 turns). Source: arxiv.org. Saturation forecast: Around July 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 43 |
| 2 | Claude Opus 4.6 (Thinking) | 41 |
| 3 | Qwen 3 235B A22B (Thinking) | 25 |
| 4 | GPT-OSS-120B | 23 |
| 5 | Intern-S1 | 10 |
Interactive version: theaggregate.ai/benchmark?slug=moldesignbench-molecule-optimization · How It Works · Data refreshed daily, snapshot 2026-09-26.