Open LMM Reasoning - DynaMath - Subject-scientific figure; Avg: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 75.6 |
| 2 | Gemini 2.0 Flash | 72 |
| 3 | GPT-4.1 Mini | 70 |
| 4 | GPT-4o ChatGPT | 70 |
| 5 | GPT-4.1 (2025-04-14) | 68 |
| 6 | InternVL3-38B | 66.2 |
| 7 | Gemini 1.5 Pro (002) | 64.9 |
| 8 | Claude 3.5 Sonnet (20241022) | 63.6 |
| 9 | Claude 3.7 Sonnet | 62 |
| 10 | QVQ-72B-Preview | 60.4 |
| 11 | InternVL3-78B | 60.2 |
| 12 | VLAA-Thinker-Qwen2.5VL-7B | 57.1 |
| 13 | InternVL3-8B | 56.7 |
| 14 | InternVL2.5-78B-CoT | 56.7 |
| 15 | Taichu-VLR-7B | 55.6 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-dynamath-subject-scientific-figure-avg · How It Works · Data refreshed daily, snapshot 2026-09-05.