Open LMM Reasoning - DynaMath - Subject-plane geometry: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 46.8 |
| 2 | GPT-4.1 Mini | 44.2 |
| 3 | GPT-4o ChatGPT | 44.2 |
| 4 | Gemini 2.0 Flash | 40.3 |
| 5 | InternVL3-78B | 39 |
| 6 | InternVL2.5-78B-CoT | 39 |
| 7 | Claude 3.7 Sonnet | 37.7 |
| 8 | Gemma 3 27B | 37.7 |
| 9 | InternVL3-38B | 36.4 |
| 10 | GPT-4.1 (2025-04-14) | 36.4 |
| 11 | InternVL3-8B | 33.8 |
| 12 | Gemini 1.5 Pro (002) | 33.8 |
| 13 | Claude 3.5 Sonnet (20241022) | 31.2 |
| 14 | Gemma 3 12B | 31.2 |
| 15 | QVQ-72B-Preview | 31.2 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-dynamath-subject-plane-geometry · How It Works · Data refreshed daily, snapshot 2026-09-05.