MEGA-Bench Task - Number Puzzle Kakuro 5x5: leaderboard

The "Number Puzzle Kakuro 5x5" subtask of MEGA-Bench Task. A single task from MEGA-Bench, a large-scale multimodal evaluation suite that scores vision-language models across 500+ real-world tasks spanning perception, reasoning, OCR, charts, documents, and multi-image understanding.

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

Top models

#ModelScoreOverall rank
1GPT-4o0#343
2Gemma 3 27B (IT)0#523
3Gemma 3 12B (IT)0#664
4Gemma 3 4B (IT)0#992
5GPT-4o Mini0#599
6Claude 3.5 Sonnet (20241022)0#291
7InternVL3-8B0#620
8Gemini 1.5 Pro (002)0#349
9Gemini 1.5 Flash (002)0#583
10Claude 3.5 Sonnet (20240620)0#299
11InternVL3-38B0#405
12InternVL3-78B0#352
13Gemini 2.5 Pro (Preview 03-25)0#123
14InternVL2-8B0#817
15MiniCPM-V-2.60#836

Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-number-puzzle-kakuro-5x5 · How It Works · Data refreshed daily, snapshot 2026-10-20.