PBSBench - Cell Multiple Choice (Out-of-Domain): leaderboard
PBSBench (2026) tests vision-language models on peripheral blood smear hematopathology, with questions about single white blood cell crops. Multiple-choice accuracy in percent on cells from three external datasets; higher is better.
Metric: Accuracy (%, times 100) on PBSBench cell-level out-of-domain multiple-choice questions about single white-blood-cell crops from peripheral blood smears (1,493 questions on cells from three external datasets); questions generated from GPT-4o morphology captions of hematopathologist-labeled cells; greedy decoding, model chat templates; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 93 | #754 |
| 2 | Gemini 2.5 Pro | 92 | #280 |
| 3 | InternVL3.5-8B | 91 | #1618 |
| 4 | Claude Sonnet 4.5 | 90 | #267 |
| 5 | Qwen 2 VL 7B Instruct | 87 | #2581 |
| 6 | Qwen 2.5 VL 7B Instruct | 84 | #1919 |
| 7 | PathGen-LLaVA | 78 | #1421 |
| 8 | DeepSeek-VL-7B | 59 | #7442 |
| 9 | llava-v1.6-mistral-7B | 58 | #4027 |
| 10 | LLaVA-1.6-Vicuna-7B | 55 | |
| 11 | Idefics3-8B-Llama3 | 44 | #5592 |
| 12 | Quilt-LLaVA | 39 | #5009 |
| 13 | LLaVA-Med | 26 | |
| 14 | Med-Flamingo | 26 | |
| 15 | BLIP2-OPT-6.7B | 22 |
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-multiple-choice-out-of-domain · How It Works · Data refreshed daily, snapshot 2026-11-22.