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
| # | Model | Score |
|---|---|---|
| 1 | Lingshu-7B | 93.41 |
| 2 | MedGemma-27B-IT | 91.83 |
| 3 | Gemini 3 Flash | 91.18 |
| 4 | Qwen 3.5 Flash | 90.98 |
| 5 | Lingshu-32B | 90.65 |
| 6 | DeepSeek V4 Flash | 90.49 |
| 7 | GPT-5.2 | 89.2 |
| 8 | MedGemma-4B | 89.06 |
| 9 | Qwen 2.5 VL 7B Instruct | 88.26 |
| 10 | MedGemma 1.5 4B | 78.13 |
Interactive version: theaggregate.ai/benchmark?slug=evipathbench-diagnostic-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-29.