MEGA-Bench Task - Code Translation Python — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 64.6 |
| 2 | Claude 3.5 Sonnet (20240620) | 64.6 |
| 3 | Claude 3.5 Sonnet (20241022) | 60.4 |
| 4 | Gemini 2.0 Flash (Preview) | 54.2 |
| 5 | Gemma 3 27B (IT) | 50 |
| 6 | InternVL3-38B | 50 |
| 7 | Gemini 2.5 Pro | 47.9 |
| 8 | InternVL3-14B | 45.8 |
| 9 | Gemini 1.5 Pro (002) | 45.8 |
| 10 | Gemma 3 12B (IT) | 43.8 |
| 11 | InternVL3-78B | 43.8 |
| 12 | Qwen 2 VL 72B | 41.7 |
| 13 | Gemini 1.5 Flash (002) | 41.7 |
| 14 | InternVL2.5-78B | 41.7 |
| 15 | InternVL3-8B | 35.4 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-code-translation-python · How the rankings work · Data refreshed daily, snapshot 2026-07-22.