PolyReal - Experiment Mechanism Reasoning: leaderboard
PolyReal (2026) evaluates multimodal models on 545 expert-written polymer science tasks covering five stages of real experimental work. Answers are scored against expert key points by an LLM judge and summarized as F1 from 0 to 1. This board is F1 on the module about reasoning about reaction diagrams and procedures; higher is better.
Metric: F1 score on the Experiment Mechanism Reasoning module of PolyReal (causal and procedural reasoning over reaction diagrams); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | O3 | 0.611 | #242 | |
| 2 | GPT-5 | 0.608 | #185 | |
| 3 | Claude Sonnet 4.5 | Thinking | 0.578 | #267 |
| 4 | Qwen 3 VL 235B A22B (Thinking) | 0.578 | #462 | |
| 5 | Grok 4 | 0.577 | #321 | |
| 6 | Qwen 3 VL 32B (Thinking) | 0.547 | #577 | |
| 7 | Gemini 2.5 Pro | 0.535 | #280 | |
| 8 | Gemini 2.5 Flash | 0.529 | #466 | |
| 9 | DeepSeek R1 | 0.48 | #484 | |
| 10 | Gemini 2.0 Flash (Thinking) | 0.466 | ||
| 11 | Intern-S1 | 0.403 | #627 | |
| 12 | GPT-4o | 0.374 | #754 | |
| 13 | Qwen 2.5 VL 72B Instruct | 0.312 | #849 | |
| 14 | GPT-4o Mini | 0.258 | #1680 | |
| 15 | DeepSeek-VL2 | 0.101 | #3056 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=polyreal-experiment-mechanism-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-22.