MEGA-Bench Task - Code Programming Test Easy — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL2.5-78B | 56.9 |
| 2 | InternVL3-38B | 55.6 |
| 3 | Gemini 2.5 Pro | 54.2 |
| 4 | Claude 3.5 Sonnet (20240620) | 54.2 |
| 5 | InternVL3-78B | 50.7 |
| 6 | InternVL3-14B | 47.9 |
| 7 | GPT-4o | 45.8 |
| 8 | Claude 3.5 Sonnet (20241022) | 45.8 |
| 9 | Gemma 3 27B (IT) | 43.8 |
| 10 | Gemini 2.0 Flash (Preview) | 37.5 |
| 11 | Qwen 2 VL 72B | 27.1 |
| 12 | Llama 4 Scout Base | 27.1 |
| 13 | InternVL3-8B | 25.7 |
| 14 | Qwen 2 VL 7B | 20.8 |
| 15 | GPT-4o Mini | 20.8 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-code-programming-test-easy · How the rankings work · Data refreshed daily, snapshot 2026-07-22.