PBSBench - Slide True/False: leaderboard

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 January 2027. 5 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.569
2GPT-4o57
3Gemini 2.5 Pro49

Interactive version: theaggregate.ai/benchmark?slug=pbsbench-slide-true-false · How It Works · Data refreshed daily, snapshot 2026-10-07.