X-PCR - Disease Diagnosis: 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 disease diagnosis stage, in percent; higher is better.

Metric: Accuracy (%) at stage 4, diagnosing the disease from the findings, 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
1Gemini 2.5 Flash74.68#466
2GPT-573.11#185
3Gemini 2.5 Pro72.48#280
4Qwen 2.5 VL 7B72.04#1878
5InternVL3-32B71.01
6GLM-4.5V70.75#756
7Qwen 3 VL 8B67.84#927
8Lingshu-7B67.41#1646
9Qwen 2.5 VL 72B67.15#782
10InternVL3-8B65.53#1795
11Qwen 3 VL 30B A3B65.14#791
12GPT-5 Nano64.41#912
13MedGemma-27B-IT64.27#1359
14Claude Haiku 4.563.23#587
15HuatuoGPT-Vision-7B59.21#2178

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-disease-diagnosis · How It Works · Data refreshed daily, snapshot 2026-11-22.