PBSBench - Cell Multiple Choice: leaderboard
Metric: Accuracy (%, times 100) on PBSBench cell-level in-domain multiple-choice questions about single white-blood-cell crops from peripheral blood smears (1,088 questions); questions generated from GPT-4o morphology captions of hematopathologist-labeled cells; greedy decoding, model chat templates; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 90 |
| 2 | Gemini 2.5 Pro | 88 |
| 3 | Qwen 2 VL 7B Instruct | 81 |
| 4 | Qwen 2.5 VL 7B Instruct | 76 |
| 5 | Claude Sonnet 4.5 | 72 |
Interactive version: theaggregate.ai/benchmark?slug=pbsbench-cell-multiple-choice · How It Works · Data refreshed daily, snapshot 2026-10-07.