X-PCR - Clinical Decision-Making: leaderboard
Metric: Accuracy (%) at stage 6, choosing management (items written by ophthalmologists), 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 2030. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 54.71 |
| 2 | GPT-5 Nano | 48.92 |
| 3 | GLM-4.5V | 46.58 |
| 4 | MedGemma-27B-IT | 45.32 |
| 5 | Claude Haiku 4.5 | 43.83 |
| 6 | Qwen 2.5 VL 7B | 38.31 |
| 7 | Gemini 2.5 Pro | 37.35 |
| 8 | InternVL3-8B | 37.22 |
| 9 | Gemini 2.5 Flash | 36.28 |
Interactive version: theaggregate.ai/benchmark?slug=x-pcr-clinical-decision-making · How It Works · Data refreshed daily, snapshot 2026-10-07.