X-PCR - Attending-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 attending difficulty, in percent; higher is better.
Metric: Accuracy (%) on the questions ophthalmologists rated at attending 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 | 76.19 | #178 |
| 2 | Qwen 3 VL 30B A3B | 70.84 | #784 |
| 3 | Gemini 2.5 Pro | 70.68 | #276 |
| 4 | InternVL3-32B | 70.37 | |
| 5 | Qwen 2.5 VL 72B | 70.11 | #781 |
| 6 | GPT-5 Nano | 69.28 | #906 |
| 7 | GLM-4.5V | 69.19 | #754 |
| 8 | Qwen 2.5 VL 7B | 68.43 | #1862 |
| 9 | InternVL3-8B | 67.3 | #1782 |
| 10 | Gemini 2.5 Flash | 65.48 | #463 |
| 11 | Lingshu-7B | 65.15 | #1635 |
| 12 | MedGemma-27B-IT | 64.63 | #1350 |
| 13 | Qwen 3 VL 8B | 61.49 | #917 |
| 14 | Claude Haiku 4.5 | 59.89 | #583 |
| 15 | HuaTuoGPT-Vision-34B | 59.31 | #1828 |
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-attending-level-questions · How It Works · Data refreshed daily, snapshot 2026-11-21.