MolViBench - Level 2 Apply: leaderboard
The Level 2 slice of MolViBench (2026), a molecular vibe coding benchmark: RDKit tasks on applying: multi-tool composition with two-step molecular transformations (72 tasks). The score is Pass@1, the percent of tasks whose generated Python code reproduces the reference output, with each model generating once without execution feedback; higher is better.
Metric: Pass@1 (%) on the 72 Level 2 tasks (Apply), direct generation in one pass with no execution feedback, 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 October 2027. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.3 Codex | 55.6 | #125 | |
| 2 | Claude Opus 4.6 | Thinking | 50 | #114 |
| 3 | Gemini 3 Pro | 45.8 | #146 | |
| 4 | GPT-5.2 Codex | 44.4 | #186 | |
| 5 | Kimi K2.5 | 43.1 | #272 | |
| 6 | MiniMax-M2.5 | 40.3 | #600 | |
| 7 | DeepSeek V3.2 | Non-reasoning | 40.3 | #425 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=molvibench-level-2-apply · How It Works · Data refreshed daily, snapshot 2026-11-22.