PBSBench - Slide True/False: leaderboard
PBSBench (2026) tests vision-language models on peripheral blood smear hematopathology, with questions about whole blood smear slides. True or false accuracy in percent; higher is better.
Metric: Accuracy (%, times 100) on PBSBench slide-level true/false questions about whole peripheral-blood-smear slides (35 questions); proprietary models see 30 sampled patches per slide, whole-slide models their own input format; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | SlideChat | 77 | |
| 2 | Claude Sonnet 4.5 | 69 | #261 |
| 3 | GPT-4o | 57 | #751 |
| 4 | Gemini 2.5 Pro | 49 | #276 |
| 5 | HistoGPT | 20 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=pbsbench-slide-true-false · How It Works · Data refreshed daily, snapshot 2026-11-21.