MEGA-Bench Task - Tweets Captioning — leaderboard

Metric: Task Score (%). Source: huggingface.co. 44 models tracked.

Top models

#ModelScore
1Claude 3.5 Sonnet (20241022)70.7
2Claude 3.5 Sonnet (20240620)65
3GPT-4o Mini61.4
4Gemini 2.5 Pro60
5GPT-4o60
6InternVL2.5-78B57.9
7Gemini 1.5 Pro (002)57.1
8InternVL3-78B56.4
9Qwen 2 VL 72B56.4
10Qwen 2 VL 7B55
11Gemini 2.0 Flash (Preview)55
12Gemini 1.5 Flash (002)52.1
13Pixtral-12B50.7
14InternVL3-14B49.3
15Llama 4 Scout Base47.9

Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-tweets-captioning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.