MolViBench: leaderboard

Molecular Vibe Coding, a paradigm where chemists interact with LLMs to generate executable programs for molecular tasks, has emerged as a flexible alternative to chemical agents with predefined tools, enabling chemists to express arbitrarily complex, customized workflows. Unlike general coding tasks, molecular coding imposes a distinctive challenge that LLMs should jointly equip programming, molec

Metric: Pass@1 rate (self-reported). Source: benchmarklist.com. Saturation forecast: Around June 2027. 15 models tracked.

Top models

#ModelScoreOverall rank
1GPT-5.2 Codex33.2#95
2GPT-5.3 Codex32.7#69
3MiniMax-M2.530.4#303
4Kimi K2.527.9#144

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=molvibench · How It Works · Data refreshed daily, snapshot 2026-10-20.