MEGA-Bench Task - Multilingual Movie Info Parsing — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 77.6 |
| 2 | Claude 3.5 Sonnet (20240620) | 74.5 |
| 3 | Gemini 2.0 Flash (Preview) | 73.5 |
| 4 | Qwen 2 VL 72B | 69.4 |
| 5 | GPT-4o | 66.3 |
| 6 | InternVL3-78B | 66.3 |
| 7 | InternVL3-14B | 66.3 |
| 8 | InternVL3-8B | 65.3 |
| 9 | Claude 3.5 Sonnet (20241022) | 65.3 |
| 10 | InternVL2.5-78B | 65.3 |
| 11 | Gemma 3 12B (IT) | 63.3 |
| 12 | InternVL3-38B | 63.3 |
| 13 | Qwen 2 VL 7B | 62.2 |
| 14 | Qwen 2 VL 2B | 62.2 |
| 15 | GPT-4o Mini | 60.2 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-multilingual-movie-info-parsing · How the rankings work · Data refreshed daily, snapshot 2026-07-22.