OmniMatBench — leaderboard
Metric: Avg. Score (self-reported). Source: benchmarklist.com. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 37.2 |
| 2 | Gemini 3.1 Pro (Preview) | 34.7 |
| 3 | GPT-5.5 | 32.4 |
| 4 | Qwen 3.6 Plus | 29.9 |
| 5 | Grok 4.3 | 29.1 |
| 6 | O3 | 28.8 |
| 7 | Gemma 4 31B | 25.7 |
| 8 | O4 Mini | 25.4 |
| 9 | Qwen 3 VL 235B A22B | 24.7 |
| 10 | GLM-4.6V | 21.2 |
| 11 | Llama 4 Maverick | 20 |
| 12 | GPT-4o | 14.6 |
Interactive version: theaggregate.ai/benchmark?slug=omnimatbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.