MEGA-Bench Task - Calendar Schedule Suggestion: leaderboard

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

Top models

#ModelScore
1Gemini 2.5 Pro (Preview 03-25)78.6
2Claude 3.5 Sonnet (20241022)64.3
3Claude 3.5 Sonnet (20240620)64.3
4GPT-4o42.9
5InternVL3-78B42.9
6InternVL3-8B35.7
7InternVL3-38B35.7
8Gemini 1.5 Pro (002)35.7
9InternVL2.5-78B35.7
10GPT-4o Mini21.4
11Gemma 3 27B (IT)14.3
12Gemma 3 12B (IT)14.3
13Gemma 3 4B (IT)14.3
14Qwen 2 VL 7B7.1
15Qwen 2 VL 2B7.1

Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-calendar-schedule-suggestion · How It Works · Data refreshed daily, snapshot 2026-09-05.