EviPathBench - Image-to-Text Matching: leaderboard
Metric: Accuracy (%) pooled over all questions (the All part of each cell) on Task 1: choosing the pathologist's finding for a slide region image among four descriptions; EviPathBench: pathologist-authored diagnostic paths on 1,822 TCGA whole-slide images (16 organs), findings at 2.5x, 10x and 40x magnification; four options per question with distractors mined from the same organ and magnification; parsed choice scored by exact match; chance 25; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 63.48 |
| 2 | Kimi K2.5 | 58.08 |
| 3 | Qwen 3.5 Flash | 54.36 |
| 4 | Lingshu-7B | 53.23 |
| 5 | GPT-5.2 | 52.23 |
| 6 | Lingshu-32B | 47.36 |
| 7 | MedGemma 1.5 4B | 36.37 |
| 8 | Qwen 2.5 VL 7B Instruct | 33.22 |
| 9 | MedGemma-4B | 31.63 |
| 10 | MedGemma-27B-IT | 27.91 |
Interactive version: theaggregate.ai/benchmark?slug=evipathbench-image-to-text-matching · How It Works · Data refreshed daily, snapshot 2026-09-29.