Open LMM Reasoning - MathVision - combinatorics — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 (2025-04-14) | 51.2 |
| 2 | GPT-4.1 Mini | 46.4 |
| 3 | GPT-4o ChatGPT | 42.9 |
| 4 | Doubao-1.5-Pro | 40.5 |
| 5 | Claude 3.7 Sonnet | 39.9 |
| 6 | Gemini 2.0 Flash | 35.7 |
| 7 | Gemma 3 27B | 33.3 |
| 8 | Gemini 1.5 Pro (002) | 32.7 |
| 9 | InternVL3-38B | 32.1 |
| 10 | QVQ-72B-Preview | 32.1 |
| 11 | InternVL3-78B | 31 |
| 12 | Claude 3.5 Sonnet (20241022) | 30.4 |
| 13 | GPT-4.1 Nano | 29.2 |
| 14 | InternVL2.5-78B | 29.2 |
| 15 | InternVL3-14B | 26.2 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathvision-combinatorics · How the rankings work · Data refreshed daily, snapshot 2026-07-22.