X-PCR - Anatomical Localization: leaderboard

X-PCR (2026) tests multimodal models on ophthalmic diagnosis as a six-stage reasoning chain over six imaging modalities, with multiple-choice questions built from 51 public datasets and checked by ophthalmologists. Accuracy at the anatomical localization stage, in percent; higher is better.

Metric: Accuracy (%) at stage 2, locating key fundus structures, on X-PCR's ophthalmic multiple-choice VQA (26,415 images from 51 public datasets, six imaging modalities, 52 diseases), zero-shot, temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 21 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-588.05#185
2Gemini 2.5 Pro84.05#280
3InternVL3-32B83.25
4Gemini 2.5 Flash82.04#466
5GLM-4.5V81.74#756
6Qwen 2.5 VL 72B81.54#782
7Qwen 3 VL 30B A3B79.33#791
8GPT-5 Nano77.82#912
9Claude Haiku 4.575.9#587
10InternVL3-8B73.97#1795
11MedGemma-27B-IT72.44#1359
12Qwen 2.5 VL 7B68.28#1878
13Lingshu-7B66.2#1646
14HuaTuoGPT-Vision-34B66.01#1840
15Qwen 3 VL 8B64.67#927

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

Interactive version: theaggregate.ai/benchmark?slug=x-pcr-anatomical-localization · How It Works · Data refreshed daily, snapshot 2026-11-22.