MolViBench — leaderboard
Metric: Pass@1 rate (self-reported). Source: benchmarklist.com. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 38.6 |
| 2 | GPT-5.2 Codex | 33.2 |
| 3 | GPT-5.3 Codex | 32.7 |
| 4 | MiniMax-M2.5 | 30.4 |
Interactive version: theaggregate.ai/benchmark?slug=molvibench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.