MEGA-Bench Task - Landmark Recognition And QA — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 75.6 |
| 2 | GPT-4o | 71.1 |
| 3 | Claude 3.5 Sonnet (20241022) | 71.1 |
| 4 | Gemini 2.0 Flash (Preview) | 71.1 |
| 5 | Gemini 1.5 Pro (002) | 66.7 |
| 6 | Qwen 2 VL 7B | 64.4 |
| 7 | Gemma 3 12B (IT) | 62.2 |
| 8 | Claude 3.5 Sonnet (20240620) | 60 |
| 9 | Gemma 3 4B (IT) | 57.8 |
| 10 | Qwen 2 VL 72B | 57.8 |
| 11 | Gemma 3 27B (IT) | 55.6 |
| 12 | Gemini 1.5 Flash (002) | 55.6 |
| 13 | InternVL3-38B | 53.3 |
| 14 | GPT-4o Mini | 53.3 |
| 15 | Pixtral-12B | 53.3 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-landmark-recognition-and-qa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.