MEGA-Bench - Application: Mathematics — leaderboard
Metric: Average Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 63.2 |
| 2 | Gemini 2.0 Flash (Preview) | 49.7 |
| 3 | Claude 3.5 Sonnet (20241022) | 47.6 |
| 4 | Claude 3.5 Sonnet (20240620) | 47.5 |
| 5 | GPT-4o | 44 |
| 6 | Gemma 3 27B (IT) | 42.2 |
| 7 | InternVL3-78B | 41.2 |
| 8 | InternVL3-38B | 41.2 |
| 9 | Gemini 1.5 Pro (002) | 41.2 |
| 10 | InternVL3-14B | 41 |
| 11 | Gemini 1.5 Flash (002) | 38.5 |
| 12 | InternVL2.5-78B | 37.7 |
| 13 | Qwen 2 VL 72B | 35.5 |
| 14 | Llama 4 Scout Base | 35.1 |
| 15 | InternVL3-8B | 34.9 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-application-mathematics · How the rankings work · Data refreshed daily, snapshot 2026-07-22.