Open LMM Reasoning - MathVerse - Analytic: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 60.5 |
| 2 | GPT-4.1 Mini | 58.1 |
| 3 | InternVL3-78B | 58.1 |
| 4 | GPT-4o ChatGPT | 55.8 |
| 5 | Claude 3.7 Sonnet | 53.5 |
| 6 | GPT-4.1 (2025-04-14) | 51.2 |
| 7 | Gemini 1.5 Pro (002) | 48.8 |
| 8 | VLAA-Thinker-Qwen2.5VL-7B | 46.5 |
| 9 | VLM-R1-3B-Math-0305 | 46.5 |
| 10 | Qwen 2 VL 72B | 44.2 |
| 11 | InternVL3-38B | 44.2 |
| 12 | Gemini 2.0 Flash | 44.2 |
| 13 | QVQ-72B-Preview | 44.2 |
| 14 | Taichu-VLR-7B | 44.2 |
| 15 | VLAA-Thinker-Qwen2.5VL-3B | 44.2 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathverse-analytic · How It Works · Data refreshed daily, snapshot 2026-09-05.