OmniMatBench - QA: leaderboard
Metric: QA macro-F1 (0-100): F1 between the response and the expert key points (precision and recall judged by Gemini 2.5 Flash), macro-averaged over subfields, times 100, over all 1,261 open-ended QA questions in the 19 subfields on OmniMatBench (3,171 expert-curated multimodal materials-science problems in 19 subfields: 1,261 open-ended QA and 1,910 calculation questions); higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 44.3 |
| 2 | Gemini 3.1 Pro (Preview) | 40.6 |
| 3 | GPT-5.5 | 39.3 |
| 4 | O3 | 37.6 |
| 5 | Grok 4.3 | 35.4 |
| 6 | Qwen 3.6 Plus | 35 |
| 7 | Gemma 4 31B | 32.1 |
| 8 | O4 Mini | 30.7 |
| 9 | Qwen 3 VL 235B A22B | 27.8 |
| 10 | GLM-4.6V | 24.9 |
| 11 | GPT-4o | 21.9 |
| 12 | Llama 4 Maverick | 20.6 |
Interactive version: theaggregate.ai/benchmark?slug=omnimatbench-qa · How It Works · Data refreshed daily, snapshot 2026-10-07.