Open LMM Reasoning - DynaMath - Subject-plane geometry; Avg — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 67.4 |
| 2 | Gemini 2.0 Flash | 66.1 |
| 3 | GPT-4o ChatGPT | 61.3 |
| 4 | GPT-4.1 Mini | 61 |
| 5 | Claude 3.7 Sonnet | 59.9 |
| 6 | Gemini 1.5 Pro (002) | 59.7 |
| 7 | Gemma 3 27B | 58.4 |
| 8 | GPT-4.1 (2025-04-14) | 57.1 |
| 9 | InternVL3-78B | 56.1 |
| 10 | Claude 3.5 Sonnet (20241022) | 56 |
| 11 | QVQ-72B-Preview | 54.4 |
| 12 | InternVL3-38B | 53.2 |
| 13 | Grok 2 (1212) | 52.1 |
| 14 | Gemma 3 12B | 51.3 |
| 15 | InternVL3-8B | 50.9 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-dynamath-subject-plane-geometry-avg · How the rankings work · Data refreshed daily, snapshot 2026-07-22.