MEGA-Bench Task - AV Multicamera Tracking Predict BBox — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 13.4 |
| 2 | Qwen 2 VL 72B | 8 |
| 3 | Gemma 3 27B (IT) | 5.4 |
| 4 | GPT-4o Mini | 4.7 |
| 5 | Gemini 2.0 Flash (Preview) | 4.5 |
| 6 | GPT-4o | 3.8 |
| 7 | Claude 3.5 Sonnet (20240620) | 3.8 |
| 8 | Qwen 2 VL 2B | 3.4 |
| 9 | Aquila-VL-2B | 3.4 |
| 10 | MiniCPM-V-2.6 | 3.4 |
| 11 | InternVL2-8B | 3.2 |
| 12 | Qwen 2 VL 7B | 2.7 |
| 13 | Gemma 3 12B (IT) | 2.4 |
| 14 | Claude 3.5 Sonnet (20241022) | 2.3 |
| 15 | Pixtral-12B | 2.2 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-av-multicamera-tracking-predict-bbox · How the rankings work · Data refreshed daily, snapshot 2026-07-22.