MEGA-Bench Task - Multilingual Ruozhiba Explanation French — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 79.3 |
| 2 | Gemini 2.0 Flash (Preview) | 73.6 |
| 3 | GPT-4o | 67.9 |
| 4 | InternVL3-78B | 65.7 |
| 5 | InternVL3-14B | 65 |
| 6 | InternVL3-38B | 64.3 |
| 7 | Claude 3.5 Sonnet (20241022) | 59.3 |
| 8 | Ovis2-8B | 56.4 |
| 9 | InternVL2.5-78B | 54.3 |
| 10 | InternVL3-8B | 50 |
| 11 | Claude 3.5 Sonnet (20240620) | 47.9 |
| 12 | Llama 4 Scout Base | 45 |
| 13 | Gemma 3 12B (IT) | 43.6 |
| 14 | GPT-4o Mini | 42.9 |
| 15 | Gemma 3 27B (IT) | 40.7 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-multilingual-ruozhiba-explanation-french · How the rankings work · Data refreshed daily, snapshot 2026-07-22.