EviPathBench - Diagnostic Reasoning: leaderboard

Metric: Accuracy (%) pooled over all questions (the All part of each cell) on Task 4: choosing the triage class, integrated diagnosis or refinement from the organ and the pathologist's findings along a diagnostic route at three magnifications (text-only reference DeepSeek-V4-Flash included); 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: Estimated already saturated. 19 models tracked.

Top models

#ModelScore
1Lingshu-7B93.41
2MedGemma-27B-IT91.83
3Gemini 3 Flash91.18
4Qwen 3.5 Flash90.98
5Lingshu-32B90.65
6DeepSeek V4 Flash90.49
7GPT-5.289.2
8MedGemma-4B89.06
9Qwen 2.5 VL 7B Instruct88.26
10MedGemma 1.5 4B78.13

Interactive version: theaggregate.ai/benchmark?slug=evipathbench-diagnostic-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-29.