Open LMM Reasoning - MathVerse - Plane Geometry: leaderboard
The "MathVerse - Plane Geometry" subtask of Open LMM Reasoning. A task from the Open LMM Reasoning leaderboard, which evaluates large multimodal models on multi-step visual, mathematical and logical reasoning problems.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 100 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Doubao-1.5-Pro | 67.5 | #287 |
| 2 | Gemini 1.5 Pro (002) | 57.6 | #349 |
| 3 | VLAA-Thinker-Qwen2.5VL-7B | 53.3 | #555 |
| 4 | InternVL3-78B | 52.4 | #352 |
| 5 | Taichu-VLR-7B | 52.4 | #526 |
| 6 | QVQ-72B-Preview | 51.6 | #440 |
| 7 | GPT-4o ChatGPT | 51.2 | |
| 8 | GPT-4.1 (2025-04-14) | 50.2 | #250 |
| 9 | Gemini 2.0 Flash | 49.4 | #342 |
| 10 | InternVL3-38B | 48.8 | #405 |
| 11 | Claude 3.5 Sonnet (20241022) | 47.6 | #291 |
| 12 | GPT-4.1 Mini | 46.7 | #355 |
| 13 | Claude 3.7 Sonnet | 46.7 | #249 |
| 14 | InternVL3-14B | 45.5 | #505 |
| 15 | Qwen 2.5 VL 7B | 44.1 | #643 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathverse-plane-geometry · How It Works · Data refreshed daily, snapshot 2026-10-20.