Open LMM Reasoning - OlympiadBench — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2 VL 72B | 10.3 |
| 2 | Qwen 2 VL 7B | 3.2 |
| 3 | Llama 3.2 11B Instruct | 1.6 |
| 4 | Qwen 2 VL 2B | 0.6 |
| 5 | InternVL2-8B | 0.3 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-olympiadbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.