Open LMM Reasoning - MathVerse - Plane Geometry — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 67.5 |
| 2 | Gemini 1.5 Pro (002) | 57.6 |
| 3 | InternVL3-78B | 52.4 |
| 4 | QVQ-72B-Preview | 51.6 |
| 5 | GPT-4o ChatGPT | 51.2 |
| 6 | GPT-4.1 (2025-04-14) | 50.2 |
| 7 | Gemini 2.0 Flash | 49.4 |
| 8 | InternVL3-38B | 48.8 |
| 9 | Ovis2-8B | 47.8 |
| 10 | Claude 3.5 Sonnet (20241022) | 47.6 |
| 11 | GPT-4.1 Mini | 46.7 |
| 12 | Claude 3.7 Sonnet | 46.7 |
| 13 | InternVL3-14B | 45.5 |
| 14 | InternVL2.5-78B | 41.2 |
| 15 | InternVL3-8B | 39.6 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathverse-plane-geometry · How the rankings work · Data refreshed daily, snapshot 2026-07-22.