MEGA-Bench - Skill: Object Recognition And Classification — leaderboard
Metric: Average Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 67.6 |
| 2 | Gemini 2.0 Flash (Preview) | 57.8 |
| 3 | Claude 3.5 Sonnet (20241022) | 56.9 |
| 4 | GPT-4o | 56.3 |
| 5 | Claude 3.5 Sonnet (20240620) | 54.1 |
| 6 | Gemini 1.5 Pro (002) | 52 |
| 7 | Qwen 2 VL 72B | 48.7 |
| 8 | InternVL3-78B | 47.1 |
| 9 | InternVL2.5-78B | 46.9 |
| 10 | InternVL3-38B | 46.8 |
| 11 | Gemini 1.5 Flash (002) | 46.4 |
| 12 | GPT-4o Mini | 44.9 |
| 13 | Gemma 3 27B (IT) | 44.4 |
| 14 | InternVL3-14B | 42.3 |
| 15 | Gemma 3 12B (IT) | 38.2 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-skill-object-recognition-and-classification · How the rankings work · Data refreshed daily, snapshot 2026-07-22.