MolViBench (Chinese Prompts): leaderboard

MolViBench (2026), a benchmark of 358 RDKit molecular coding tasks, with every task prompt given in Chinese instead of English and the code generated in one pass. The score is Pass@1 against the reference outputs, in percent; higher is better.

Metric: Pass@1 (%) over all 358 tasks with the task prompts in Chinese, direct generation, RDKit molecular coding tasks answered by generated Python code, official APIs, temperature 0, at most 4,096 output tokens; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 4 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Opus 4.638.3#113
2Gemini 3 Pro37.7#145
3GPT-5.3 Codex36.9#124
4DeepSeek V3.2Non-reasoning33.2#419

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

Interactive version: theaggregate.ai/benchmark?slug=molvibench-chinese-prompts · How It Works · Data refreshed daily, snapshot 2026-11-21.