MEGA-Bench Task - Booking Web Recommendation — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 78 |
| 2 | Claude 3.5 Sonnet (20240620) | 76.2 |
| 3 | Gemini 2.5 Pro | 74.2 |
| 4 | Gemini 2.0 Flash (Preview) | 71.2 |
| 5 | GPT-4o Mini | 70.6 |
| 6 | Gemini 1.5 Pro (002) | 67.7 |
| 7 | Claude 3.5 Sonnet (20241022) | 67.5 |
| 8 | InternVL2.5-78B | 63.1 |
| 9 | Gemini 1.5 Flash (002) | 62 |
| 10 | Pixtral-12B | 59.9 |
| 11 | Gemma 3 12B (IT) | 55.3 |
| 12 | InternVL3-14B | 55 |
| 13 | Gemma 3 27B (IT) | 54 |
| 14 | Llama 4 Scout Base | 48.3 |
| 15 | Gemma 3 4B (IT) | 48.1 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-booking-web-recommendation · How the rankings work · Data refreshed daily, snapshot 2026-07-22.