X-PCR - Specialist-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 specialist difficulty, in percent; higher is better.
Metric: Accuracy (%) on the questions ophthalmologists rated at specialist 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 | 62.92 | #185 |
| 2 | Qwen 2.5 VL 72B | 55.69 | #782 |
| 3 | Gemini 2.5 Pro | 54.76 | #280 |
| 4 | InternVL3-32B | 52.37 | |
| 5 | Qwen 3 VL 30B A3B | 52.23 | #791 |
| 6 | GPT-5 Nano | 50.75 | #912 |
| 7 | Claude Haiku 4.5 | 50.48 | #587 |
| 8 | Gemini 2.5 Flash | 49.03 | #466 |
| 9 | Qwen 3 VL 8B | 48.93 | #927 |
| 10 | InternVL3-8B | 48.33 | #1795 |
| 11 | GLM-4.5V | 47.45 | #756 |
| 12 | MedGemma-27B-IT | 46.14 | #1359 |
| 13 | Qwen 2.5 VL 7B | 45.55 | #1878 |
| 14 | HuaTuoGPT-Vision-34B | 41.95 | #1840 |
| 15 | Lingshu-7B | 41.89 | #1646 |
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-specialist-level-questions · How It Works · Data refreshed daily, snapshot 2026-11-22.