Open LMM Reasoning - DynaMath - Subject-arithmetic: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 Mini | 57.7 |
| 2 | GPT-4o ChatGPT | 53.8 |
| 3 | Doubao-1.5-Pro | 50 |
| 4 | GPT-4.1 (2025-04-14) | 46.2 |
| 5 | Gemini 2.0 Flash | 38.5 |
| 6 | Taichu-VLR-7B | 38.5 |
| 7 | InternVL3-8B | 34.6 |
| 8 | Claude 3.5 Sonnet (20241022) | 34.6 |
| 9 | Claude 3.7 Sonnet | 34.6 |
| 10 | InternVL3-78B | 30.8 |
| 11 | Gemini 1.5 Pro (002) | 30.8 |
| 12 | GPT-4.1 Nano | 30.8 |
| 13 | Gemma 3 27B | 30.8 |
| 14 | VLAA-Thinker-Qwen2.5VL-7B | 30.8 |
| 15 | InternVL2.5-78B-CoT | 30.8 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-dynamath-subject-arithmetic · How It Works · Data refreshed daily, snapshot 2026-09-05.