Open LMM Reasoning - DynaMath - Subject-graph theory — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o ChatGPT | 43.8 |
| 2 | GPT-4.1 Mini | 33.3 |
| 3 | GPT-4.1 (2025-04-14) | 31.2 |
| 4 | Claude 3.7 Sonnet | 27.1 |
| 5 | Doubao-1.5-Pro | 22.9 |
| 6 | Qwen 2 VL 72B | 20.8 |
| 7 | Claude 3.5 Sonnet (20241022) | 20.8 |
| 8 | GPT-4.1 Nano | 18.8 |
| 9 | Gemini 2.0 Flash | 18.8 |
| 10 | Gemini 1.5 Pro (002) | 16.7 |
| 11 | Grok 2 (1212) | 16.7 |
| 12 | Qwen 2 VL 7B | 14.6 |
| 13 | InternVL3-38B | 14.6 |
| 14 | Gemma 3 27B | 14.6 |
| 15 | InternVL2-8B | 12.5 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-dynamath-subject-graph-theory · How the rankings work · Data refreshed daily, snapshot 2026-07-22.