MEGA-Bench Task - App Layout Understanding Amazon — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 100 |
| 2 | GPT-4o | 92.9 |
| 3 | Claude 3.5 Sonnet (20240620) | 85.7 |
| 4 | InternVL3-78B | 71.4 |
| 5 | InternVL3-14B | 71.4 |
| 6 | Claude 3.5 Sonnet (20241022) | 71.4 |
| 7 | Qwen 2 VL 72B | 64.3 |
| 8 | InternVL3-38B | 64.3 |
| 9 | InternVL2.5-78B | 64.3 |
| 10 | Gemini 2.0 Flash (Preview) | 57.1 |
| 11 | InternVL3-8B | 42.9 |
| 12 | Pixtral-12B | 42.9 |
| 13 | GPT-4o Mini | 21.4 |
| 14 | Gemini 1.5 Pro (002) | 21.4 |
| 15 | Gemma 3 4B (IT) | 7.1 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-app-layout-understanding-amazon · How the rankings work · Data refreshed daily, snapshot 2026-07-22.