MEGA-Bench Task - Stack Overflow Debug QA — leaderboard
Metric: Task Score (%). Source: huggingface.co. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL3-78B | 71.4 |
| 2 | Llama 4 Scout Base | 69 |
| 3 | InternVL3-14B | 66.7 |
| 4 | Gemma 3 27B (IT) | 64.3 |
| 5 | Gemini 2.0 Flash (Preview) | 64.3 |
| 6 | InternVL3-8B | 59.5 |
| 7 | InternVL3-38B | 59.5 |
| 8 | Ovis2-8B | 59.5 |
| 9 | Gemini 2.5 Pro | 54.8 |
| 10 | Gemma 3 12B (IT) | 54.8 |
| 11 | Gemma 3 4B (IT) | 54.8 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-stack-overflow-debug-qa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.