Open LMM Reasoning - OlympiadBench - Probability and Statistics — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2 VL 72B | 26.7 |
| 2 | Qwen 2 VL 7B | 6.7 |
| 3 | Llama 3.2 11B Instruct | 3.3 |
| 4 | Qwen 2 VL 2B | 0.8 |
| 5 | InternVL2-8B | 0.4 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-olympiadbench-probability-and-statistics · How the rankings work · Data refreshed daily, snapshot 2026-07-22.