Open LMM Reasoning - MathVision - algebra: leaderboard
The "MathVision - algebra" 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 | GPT-4.1 Mini | 58.6 | #355 |
| 2 | GPT-4.1 (2025-04-14) | 58.6 | #250 |
| 3 | Doubao-1.5-Pro | 57.4 | #287 |
| 4 | GPT-4o ChatGPT | 56.2 | |
| 5 | Claude 3.7 Sonnet | 55.1 | #249 |
| 6 | Gemini 2.0 Flash | 51.6 | #342 |
| 7 | Gemini 1.5 Pro (002) | 49.3 | #349 |
| 8 | InternVL3-78B | 48.4 | #352 |
| 9 | QVQ-72B-Preview | 45.2 | #440 |
| 10 | Claude 3.5 Sonnet (20241022) | 42 | #291 |
| 11 | Gemma 3 27B | 41.4 | #607 |
| 12 | InternVL2.5-78B-CoT | 41.4 | #469 |
| 13 | InternVL3-38B | 40.9 | #405 |
| 14 | GPT-4.1 Nano | 39.1 | #731 |
| 15 | InternVL3-14B | 38.6 | #505 |
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-mathvision-algebra · How It Works · Data refreshed daily, snapshot 2026-10-20.