Open LMM Reasoning - DynaMath - Subject-graph theory; Avg — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o ChatGPT | 75.4 |
| 2 | GPT-4.1 Mini | 73.5 |
| 3 | GPT-4.1 (2025-04-14) | 69 |
| 4 | Claude 3.7 Sonnet | 62.1 |
| 5 | Gemini 2.0 Flash | 59.4 |
| 6 | Doubao-1.5-Pro | 59.4 |
| 7 | Claude 3.5 Sonnet (20241022) | 58.5 |
| 8 | Gemini 1.5 Pro (002) | 55.8 |
| 9 | GPT-4.1 Nano | 51.7 |
| 10 | InternVL3-38B | 50.6 |
| 11 | InternVL3-78B | 50.4 |
| 12 | Grok 2 (1212) | 49.6 |
| 13 | InternVL2.5-78B | 48.1 |
| 14 | Qwen 2 VL 7B | 47.5 |
| 15 | Qwen 2 VL 72B | 46.7 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-dynamath-subject-graph-theory-avg · How the rankings work · Data refreshed daily, snapshot 2026-07-22.