Open LMM Reasoning - MathVerse - Angle — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 68.4 |
| 2 | Gemini 1.5 Pro (002) | 55.4 |
| 3 | Gemini 2.0 Flash | 52.3 |
| 4 | QVQ-72B-Preview | 49.7 |
| 5 | InternVL3-78B | 49.2 |
| 6 | Claude 3.5 Sonnet (20241022) | 47.7 |
| 7 | InternVL2.5-78B | 46.6 |
| 8 | InternVL3-38B | 46.1 |
| 9 | GPT-4.1 (2025-04-14) | 45.1 |
| 10 | Ovis2-8B | 44.6 |
| 11 | GPT-4o ChatGPT | 44.6 |
| 12 | InternVL3-14B | 43 |
| 13 | Qwen 2 VL 72B | 41.5 |
| 14 | Claude 3.7 Sonnet | 40.4 |
| 15 | GPT-4.1 Mini | 37.3 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathverse-angle · How the rankings work · Data refreshed daily, snapshot 2026-07-22.