X-PCR - Resident-Level Questions: 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 on questions rated at resident difficulty, in percent; higher is better.
Metric: Accuracy (%) on the questions ophthalmologists rated at resident difficulty, 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 80.64 | #178 |
| 2 | GLM-4.5V | 77.91 | #754 |
| 3 | InternVL3-32B | 77.1 | |
| 4 | Gemini 2.5 Pro | 75.71 | #276 |
| 5 | Qwen 2.5 VL 72B | 74.89 | #781 |
| 6 | Qwen 2.5 VL 7B | 74.81 | #1862 |
| 7 | MedGemma-27B-IT | 74.19 | #1350 |
| 8 | Gemini 2.5 Flash | 73.29 | #463 |
| 9 | GPT-5 Nano | 73.23 | #906 |
| 10 | Qwen 3 VL 30B A3B | 72.8 | #784 |
| 11 | Qwen 3 VL 8B | 72.73 | #917 |
| 12 | InternVL3-8B | 70.73 | #1782 |
| 13 | Lingshu-7B | 70.18 | #1635 |
| 14 | LLaVA-Next-LLaMA3-8B | 67.83 | #5654 |
| 15 | ShareGPT4V-7B | 67.51 | #7829 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=x-pcr-resident-level-questions · How It Works · Data refreshed daily, snapshot 2026-11-21.