Med-R2 - Anatomy Level: leaderboard

Accuracy (%) of medical vision-language models on the Med-R2 (2026) anatomy level task, locating and identifying anatomy, with equal numbers of positive, negative and neutral adversarial question forms; higher is better.

Metric: Accuracy (%) on the Med-R2 Anatomy Level task (locating and identifying anatomy), zero-shot with system prompts; each task mixes equal numbers of positive, negative and neutral adversarial question forms; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 14 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Hulu-Med-14B68.1#1621
2HuaTuoGPT-Vision-34B65.9#1840
3GPT-5.2Thinking65.6#190
4Qwen 3 VL 235B A22B64.2#486
5Qwen 3 VL 8B63.3#927
6InternVL3.5-8B61#1618
7HuluMed-7B60.7#2061
8Hulu-Med-4B60.3#2410
9HuatuoGPT-Vision-7B58.7#2178
10GPT-4o56.1#754
11Lingshu-7B56#1646
12Qwen 2.5 VL 7B Instruct51.5#1919
13Janus-Pro-7B51.3#6889
14MedGemma-4B36.4#2579

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=med-r2-anatomy-level · How It Works · Data refreshed daily, snapshot 2026-11-22.