Open LMM Reasoning - DynaMath - Subject-solid geometry; Avg — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 58.7 |
| 2 | Gemini 2.0 Flash | 54.7 |
| 3 | GPT-4o ChatGPT | 54.7 |
| 4 | GPT-4.1 (2025-04-14) | 54 |
| 5 | GPT-4.1 Mini | 52 |
| 6 | Claude 3.7 Sonnet | 51.3 |
| 7 | Gemma 3 27B | 51.3 |
| 8 | Claude 3.5 Sonnet (20241022) | 50.7 |
| 9 | Gemini 1.5 Pro (002) | 50.7 |
| 10 | QVQ-72B-Preview | 48.7 |
| 11 | Gemma 3 12B | 46.7 |
| 12 | GPT-4.1 Nano | 44.7 |
| 13 | Grok 2 (1212) | 42.7 |
| 14 | InternVL3-14B | 42 |
| 15 | InternVL3-8B | 39.3 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-dynamath-subject-solid-geometry-avg · How the rankings work · Data refreshed daily, snapshot 2026-07-22.