PBSBench - Cell True/False: leaderboard
PBSBench (2026) tests vision-language models on peripheral blood smear hematopathology, with questions about single white blood cell crops. True or false accuracy in percent on in-domain cells; higher is better.
Metric: Accuracy (%, times 100) on PBSBench cell-level in-domain true/false questions about single white-blood-cell crops from peripheral blood smears (957 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 June 2028. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 77 | #754 |
| 2 | InternVL3.5-8B | 73 | #1618 |
| 3 | Gemini 2.5 Pro | 70 | #280 |
| 4 | Qwen 2 VL 7B Instruct | 67 | #2581 |
| 5 | PathGen-LLaVA | 65 | #1421 |
| 6 | Qwen 2.5 VL 7B Instruct | 63 | #1919 |
| 7 | DeepSeek-VL-7B | 63 | #7442 |
| 8 | Quilt-LLaVA | 61 | #5009 |
| 9 | Claude Sonnet 4.5 | 59 | #267 |
| 10 | Idefics3-8B-Llama3 | 59 | #5592 |
| 11 | llava-v1.6-mistral-7B | 59 | #4027 |
| 12 | LLaVA-1.6-Vicuna-7B | 58 | |
| 13 | LLaVA-Med | 54 | |
| 14 | BLIP2-OPT-6.7B | 51 | |
| 15 | Med-Flamingo | 45 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=pbsbench-cell-true-false · How It Works · Data refreshed daily, snapshot 2026-11-22.