PolyReal - Foundational Knowledge Application: 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 applying core principles to real experimental scenarios; higher is better.

Metric: F1 score on the Foundational Knowledge Application module of PolyReal (applying core scientific principles to real scenarios); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1O30.641#242
2GPT-50.594#185
3Claude Sonnet 4.5Thinking0.58#267
4Gemini 2.5 Pro0.57#280
5Grok 40.57#321
6Qwen 3 VL 235B A22B (Thinking)0.567#462
7Qwen 3 VL 32B (Thinking)0.554#577
8DeepSeek R10.551#484
9Gemini 2.5 Flash0.53#466
10Gemini 2.0 Flash (Thinking)0.509
11Intern-S10.468#627
12GPT-4o0.386#754
13Qwen 2.5 VL 72B Instruct0.37#849
14GPT-4o Mini0.346#1680
15DeepSeek-VL20.158#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-foundational-knowledge-application · How It Works · Data refreshed daily, snapshot 2026-11-22.