MEGA-Bench Task - Soccer Offside: leaderboard

The "Soccer Offside" 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. Saturation forecast: Not forecast. 44 models tracked.

Top models

#ModelScoreOverall rank
1InternVL3-38B55.6#405
2Gemini 2.0 Flash (Preview)55.6#370
3Claude 3.5 Sonnet (20241022)44.4#291
4Gemini 2.5 Pro (Preview 03-25)44.4#123
5Gemma 3 27B (IT)33.3#523
6Gemma 3 12B (IT)33.3#664
7GPT-4o Mini33.3#599
8Gemini 1.5 Pro (002)33.3#349
9InternVL2-8B33.3#817
10MiniCPM-V-2.633.3#836
11Qwen 2 VL 72B33.3#460
12Pixtral-12B33.3#808
13Qwen 2 VL 2B33.3#1220
14Aquila-VL-2B33.3#1238
15InternVL2.5-78B33.3#431

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-soccer-offside · How It Works · Data refreshed daily, snapshot 2026-10-20.