MEGA-Bench Task - Multilingual Ruozhiba Explanation Spanish — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 81.4 |
| 2 | Gemini 2.0 Flash (Preview) | 74.3 |
| 3 | GPT-4o | 71.4 |
| 4 | InternVL3-38B | 66.4 |
| 5 | InternVL3-14B | 62.9 |
| 6 | Claude 3.5 Sonnet (20241022) | 60.7 |
| 7 | InternVL3-78B | 58.6 |
| 8 | InternVL2.5-78B | 57.1 |
| 9 | Ovis2-8B | 55 |
| 10 | Claude 3.5 Sonnet (20240620) | 49.3 |
| 11 | InternVL3-8B | 45.7 |
| 12 | Qwen 2 VL 72B | 45.7 |
| 13 | Qwen 2 VL 7B | 41.4 |
| 14 | Gemma 3 12B (IT) | 38.6 |
| 15 | InternVL2-8B | 38.6 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-multilingual-ruozhiba-explanation-spanish · How the rankings work · Data refreshed daily, snapshot 2026-07-22.