MEGA-Bench Task - Autorater Artifact Reason — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 80 |
| 2 | Gemma 3 27B (IT) | 80 |
| 3 | InternVL3-78B | 80 |
| 4 | GPT-4o | 66.7 |
| 5 | Ovis2-8B | 66.7 |
| 6 | Gemini 2.0 Flash (Preview) | 66.7 |
| 7 | Gemma 3 4B (IT) | 60 |
| 8 | InternVL3-8B | 60 |
| 9 | Claude 3.5 Sonnet (20241022) | 60 |
| 10 | Gemini 1.5 Flash (002) | 60 |
| 11 | InternVL2.5-2B | 60 |
| 12 | Gemma 3 12B (IT) | 53.3 |
| 13 | InternVL3-14B | 53.3 |
| 14 | Aquila-VL-2B | 53.3 |
| 15 | GPT-4o Mini | 53.3 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-autorater-artifact-reason · How the rankings work · Data refreshed daily, snapshot 2026-07-22.