Open LMM Reasoning - MathVerse - Functions: leaderboard
The "MathVerse - Functions" 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 | 64.8 | #287 |
| 2 | GPT-4.1 Mini | 59.1 | #355 |
| 3 | Gemini 1.5 Pro (002) | 58.5 | #349 |
| 4 | GPT-4.1 (2025-04-14) | 58.5 | #250 |
| 5 | Gemini 2.0 Flash | 57.9 | #342 |
| 6 | GPT-4o ChatGPT | 57.9 | |
| 7 | InternVL3-78B | 56.6 | #352 |
| 8 | InternVL3-38B | 54.1 | #405 |
| 9 | Claude 3.7 Sonnet | 52.8 | #249 |
| 10 | QVQ-72B-Preview | 52.2 | #440 |
| 11 | Claude 3.5 Sonnet (20241022) | 50.9 | #291 |
| 12 | Qwen 2 VL 72B | 49.1 | #460 |
| 13 | InternVL2.5-78B | 49.1 | #431 |
| 14 | Taichu-VLR-7B | 48.4 | #526 |
| 15 | InternVL2.5-78B-CoT | 47.8 | #469 |
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-functions · How It Works · Data refreshed daily, snapshot 2026-10-20.