Open LMM Reasoning - WeMath - CompleteMastery (Loose) — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 75.6 |
| 2 | GPT-4.1 (2025-04-14) | 65.1 |
| 3 | GPT-4o ChatGPT | 64.2 |
| 4 | Claude 3.7 Sonnet | 62.3 |
| 5 | InternVL3-38B | 61 |
| 6 | Gemini 1.5 Pro (002) | 60.4 |
| 7 | Gemini 2.0 Flash | 59.6 |
| 8 | InternVL3-78B | 57 |
| 9 | InternVL3-14B | 56.2 |
| 10 | Claude 3.5 Sonnet (20241022) | 56.2 |
| 11 | QVQ-72B-Preview | 55.8 |
| 12 | InternVL2.5-78B | 52.8 |
| 13 | Gemma 3 27B | 50.9 |
| 14 | InternVL3-8B | 50.7 |
| 15 | Grok 2 (1212) | 49.3 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-wemath-completemastery-loose · How the rankings work · Data refreshed daily, snapshot 2026-07-22.