MEGA-Bench Task - Funny Image Title: leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2 VL 72B | 75 |
| 2 | GPT-4o | 69.3 |
| 3 | Claude 3.5 Sonnet (20240620) | 69.3 |
| 4 | Qwen 2 VL 7B | 66.4 |
| 5 | InternVL2.5-78B | 66.4 |
| 6 | GPT-4o Mini | 65 |
| 7 | Llama 4 Scout Base | 65 |
| 8 | Claude 3.5 Sonnet (20241022) | 63.6 |
| 9 | InternVL3-78B | 62.9 |
| 10 | InternVL3-38B | 62.9 |
| 11 | Gemini 2.5 Pro (Preview 03-25) | 62.1 |
| 12 | Gemini 1.5 Flash (002) | 59.3 |
| 13 | InternVL2-8B | 58.6 |
| 14 | Gemini 1.5 Pro (002) | 57.1 |
| 15 | InternVL3-8B | 56.4 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-funny-image-title · How It Works · Data refreshed daily, snapshot 2026-09-05.