PolyReal - Lab Safety Analysis: leaderboard
Metric: F1 score on the Lab Safety Analysis module of PolyReal (risk identification in cluttered lab scenes); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 | 0.41 |
| 2 | GPT-5 | 0.37 |
| 3 | Gemini 2.5 Pro | 0.37 |
| 4 | Gemini 2.5 Flash | 0.37 |
| 5 | Qwen 3 VL 235B A22B (Thinking) | 0.35 |
| 6 | Claude Sonnet 4.5 (Thinking) | 0.32 |
| 7 | Gemini 2.0 Flash (Thinking) | 0.27 |
| 8 | Qwen 3 VL 32B (Thinking) | 0.23 |
| 9 | Grok 4 | 0.22 |
| 10 | Qwen 2.5 VL 72B Instruct | 0.14 |
| 11 | DeepSeek R1 | 0.14 |
| 12 | GPT-4o | 0.12 |
| 13 | GPT-4o Mini | 0.08 |
Interactive version: theaggregate.ai/benchmark?slug=polyreal-lab-safety-analysis · How It Works · Data refreshed daily, snapshot 2026-10-07.