VIPER (Veterinary Pathology): leaderboard
Metric: Overall score (%; mean of the MCQ, KPrim and free-text scores over 1,251 questions written and validated by board-certified veterinary pathologists on 419 H&E-stained rat histology images from seven organ systems). Source: arxiv.org. Saturation forecast: Around December 2026. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 56 |
| 2 | Gemma 4 31B (IT) | 54.4 |
| 3 | Qwen 3.5 27B | 52.4 |
| 4 | Claude Sonnet 4.6 | 48.2 |
| 5 | GPT-5.4 Mini | 48 |
| 6 | Gemini 2.5 Flash | 41 |
| 7 | GPT-5.4 Nano | 27.4 |
| 8 | MedGemma 1.5 4B | 24.8 |
Interactive version: theaggregate.ai/benchmark?slug=viper-veterinary-pathology · How It Works · Data refreshed daily, snapshot 2026-09-29.