MEGA-Bench Task - Medical Blood Vessels Recognition: leaderboard

The "Medical Blood Vessels 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
1Gemini 2.5 Pro (Preview 03-25)75#123
2MiniCPM-V-2.671.4#836
3Gemini 2.0 Flash (Preview)71.4#370
4GPT-4o67.9#343
5Gemma 3 27B (IT)67.9#523
6Gemini 1.5 Flash (002)67.9#583
7Gemma 3 12B (IT)64.3#664
8Gemma 3 4B (IT)64.3#992
9InternVL3-8B64.3#620
10Gemini 1.5 Pro (002)64.3#349
11Claude 3.5 Sonnet (20240620)64.3#299
12InternVL3-38B60.7#405
13Qwen 2 VL 7B60.7#750
14Qwen 2 VL 72B60.7#460
15Claude 3.5 Sonnet (20241022)57.1#291

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-blood-vessels-recognition · How It Works · Data refreshed daily, snapshot 2026-10-20.