Open LMM Reasoning - DynaMath - Subject-statistics — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o ChatGPT | 60 |
| 2 | GPT-4.1 Mini | 58.4 |
| 3 | GPT-4.1 (2025-04-14) | 57.6 |
| 4 | Claude 3.7 Sonnet | 52.8 |
| 5 | Claude 3.5 Sonnet (20241022) | 51.2 |
| 6 | Doubao-1.5-Pro | 51.2 |
| 7 | Gemini 2.0 Flash | 49.6 |
| 8 | InternVL3-78B | 47.2 |
| 9 | InternVL3-38B | 44 |
| 10 | InternVL3-14B | 43.2 |
| 11 | Gemini 1.5 Pro (002) | 40 |
| 12 | QVQ-72B-Preview | 38.4 |
| 13 | Grok 2 (1212) | 36 |
| 14 | GPT-4.1 Nano | 32.8 |
| 15 | InternVL3-8B | 30.4 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-dynamath-subject-statistics · How the rankings work · Data refreshed daily, snapshot 2026-07-22.