Open LMM Reasoning - MathVerse - Volume — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 68.6 |
| 2 | Gemini 1.5 Pro (002) | 47.1 |
| 3 | Claude 3.7 Sonnet | 45.1 |
| 4 | InternVL3-78B | 43.1 |
| 5 | InternVL3-38B | 43.1 |
| 6 | GPT-4.1 Mini | 39.2 |
| 7 | GPT-4o ChatGPT | 39.2 |
| 8 | QVQ-72B-Preview | 39.2 |
| 9 | InternVL3-8B | 37.3 |
| 10 | Claude 3.5 Sonnet (20241022) | 37.3 |
| 11 | Gemini 2.0 Flash | 35.3 |
| 12 | GPT-4.1 (2025-04-14) | 33.3 |
| 13 | InternVL3-14B | 31.4 |
| 14 | Grok 2 (1212) | 31.4 |
| 15 | Gemma 3 4B | 29.4 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathverse-volume · How the rankings work · Data refreshed daily, snapshot 2026-07-22.