MEGA-Bench Task - Face Identity Matching — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 100 |
| 2 | Claude 3.5 Sonnet (20241022) | 86.7 |
| 3 | Gemini 1.5 Pro (002) | 86.7 |
| 4 | Gemini 2.0 Flash (Preview) | 86.7 |
| 5 | Gemini 1.5 Flash (002) | 73.3 |
| 6 | GPT-4o | 66.7 |
| 7 | InternVL3-78B | 60 |
| 8 | Gemma 3 27B (IT) | 53.3 |
| 9 | Claude 3.5 Sonnet (20240620) | 53.3 |
| 10 | InternVL3-38B | 33.3 |
| 11 | Qwen 2 VL 72B | 26.7 |
| 12 | Gemma 3 12B (IT) | 20 |
| 13 | GPT-4o Mini | 20 |
| 14 | Gemma 3 4B (IT) | 13.3 |
| 15 | Qwen 2 VL 2B | 6.7 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-face-identity-matching · How the rankings work · Data refreshed daily, snapshot 2026-07-22.