MEGA-Bench Task - App Interactive Operations Amazon — 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) | 92.9 |
| 3 | Gemini 2.0 Flash (Preview) | 92.9 |
| 4 | Qwen 2 VL 72B | 71.4 |
| 5 | InternVL2.5-78B | 57.1 |
| 6 | GPT-4o | 50 |
| 7 | Gemini 1.5 Flash (002) | 50 |
| 8 | Claude 3.5 Sonnet (20240620) | 50 |
| 9 | GPT-4o Mini | 42.9 |
| 10 | Gemini 1.5 Pro (002) | 42.9 |
| 11 | Qwen 2 VL 7B | 35.7 |
| 12 | InternVL3-14B | 28.6 |
| 13 | InternVL3-78B | 21.4 |
| 14 | Gemma 3 27B (IT) | 14.3 |
| 15 | InternVL3-8B | 14.3 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-app-interactive-operations-amazon · How the rankings work · Data refreshed daily, snapshot 2026-07-22.