Open LMM Reasoning - DynaMath - Subject-solid geometry: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 Mini | 40 |
| 2 | Gemini 2.0 Flash | 40 |
| 3 | GPT-4.1 (2025-04-14) | 40 |
| 4 | Doubao-1.5-Pro | 40 |
| 5 | Claude 3.5 Sonnet (20241022) | 33.3 |
| 6 | Gemini 1.5 Pro (002) | 33.3 |
| 7 | Gemma 3 27B | 33.3 |
| 8 | Grok 2 (1212) | 33.3 |
| 9 | GPT-4o ChatGPT | 33.3 |
| 10 | InternVL3-8B | 26.7 |
| 11 | Claude 3.7 Sonnet | 26.7 |
| 12 | Gemma 3 12B | 26.7 |
| 13 | QVQ-72B-Preview | 26.7 |
| 14 | VLAA-Thinker-Qwen2.5VL-3B | 26.7 |
| 15 | InternVL3-78B | 20 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-dynamath-subject-solid-geometry · How It Works · Data refreshed daily, snapshot 2026-09-05.