PolyReal: 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 the overall F1 across all five modules; higher is better.
Metric: Overall F1 score of the key-point PRF framework (completeness and correctness against expert Key Points, LLM-judged) over the five PolyReal workflow modules, 545 questions, zero-shot, temperature 0; 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 | 0.601 | #237 | |
| 2 | GPT-5 | 0.578 | #178 | |
| 3 | Claude Sonnet 4.5 | Thinking | 0.546 | #261 |
| 4 | Qwen 3 VL 235B A22B (Thinking) | 0.538 | #459 | |
| 5 | Gemini 2.5 Pro | 0.536 | #276 | |
| 6 | Grok 4 | 0.533 | #319 | |
| 7 | Qwen 3 VL 32B (Thinking) | 0.525 | #573 | |
| 8 | Gemini 2.5 Flash | 0.512 | #463 | |
| 9 | DeepSeek R1 | 0.484 | #482 | |
| 10 | Gemini 2.0 Flash (Thinking) | 0.468 | ||
| 11 | Intern-S1 | 0.427 | #624 | |
| 12 | GPT-4o | 0.367 | #751 | |
| 13 | Qwen 2.5 VL 72B Instruct | 0.337 | #841 | |
| 14 | GPT-4o Mini | 0.299 | #1667 | |
| 15 | DeepSeek-VL2 | 0.132 | #2927 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=polyreal · How It Works · Data refreshed daily, snapshot 2026-11-21.