MEGA-Bench Task - Medical Abdomen MRI Organ Recognition: leaderboard

The "Medical Abdomen MRI Organ Recognition" 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: Around January 2027. 44 models tracked.

Top models

#ModelScoreOverall rank
1GPT-4o53#343
2Gemini 2.5 Pro (Preview 03-25)47#123
3Gemini 2.0 Flash (Preview)39.9#370
4Qwen 2 VL 72B38.1#460
5InternVL2.5-78B33.9#431
6Claude 3.5 Sonnet (20241022)31.5#291
7Gemini 1.5 Pro (002)29.2#349
8Gemini 1.5 Flash (002)27.4#583
9GLM-4.1V-9B (Thinking)26.2#472 (GLM-4.1V-9B)
10Claude 3.5 Sonnet (20240620)25#299
11Pixtral-12B23.8#808
12InternVL3-38B22.6#405
13GPT-4o Mini21.4#599
14InternVL3-78B18.5#352
15Gemma 3 12B (IT)17.3#664

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-medical-abdomen-mri-organ-recognition · How It Works · Data refreshed daily, snapshot 2026-10-20.