Open LMM Reasoning - DynaMath - Level-undergraduate — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o ChatGPT | 47.8 |
| 2 | GPT-4.1 Mini | 41.6 |
| 3 | GPT-4.1 (2025-04-14) | 41 |
| 4 | Claude 3.7 Sonnet | 36.6 |
| 5 | Doubao-1.5-Pro | 36 |
| 6 | Gemini 2.0 Flash | 34.2 |
| 7 | Claude 3.5 Sonnet (20241022) | 31.7 |
| 8 | InternVL3-38B | 29.2 |
| 9 | InternVL3-78B | 28 |
| 10 | InternVL3-14B | 26.7 |
| 11 | Gemini 1.5 Pro (002) | 26.7 |
| 12 | QVQ-72B-Preview | 26.1 |
| 13 | Gemma 3 27B | 21.7 |
| 14 | Grok 2 (1212) | 21.1 |
| 15 | InternVL3-8B | 20.5 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-dynamath-level-undergraduate · How the rankings work · Data refreshed daily, snapshot 2026-07-22.