PolyReal - Performance and Application Exploration: leaderboard
Metric: F1 score on the Performance and Application Exploration module of PolyReal (structure-property reasoning and material suitability); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 0.62 |
| 2 | O3 | 0.61 |
| 3 | Gemini 2.5 Pro | 0.56 |
| 4 | Grok 4 | 0.54 |
| 5 | Claude Sonnet 4.5 (Thinking) | 0.54 |
| 6 | Qwen 3 VL 32B (Thinking) | 0.54 |
| 7 | Qwen 3 VL 235B A22B (Thinking) | 0.52 |
| 8 | Gemini 2.5 Flash | 0.5 |
| 9 | Gemini 2.0 Flash (Thinking) | 0.47 |
| 10 | DeepSeek R1 | 0.43 |
| 11 | Qwen 2.5 VL 72B Instruct | 0.4 |
| 12 | GPT-4o | 0.37 |
| 13 | GPT-4o Mini | 0.35 |
Interactive version: theaggregate.ai/benchmark?slug=polyreal-performance-and-application-exploration · How It Works · Data refreshed daily, snapshot 2026-10-07.