List your company

Cell-Level Visual Question Answering on PBSBench (In-domain)

77True/False AccuracyGPT-4o
37.4847.745868.26Apr 19, 2026

Evaluation results

MethodLinks
GPT-4oModel Category=Proprietary VL Models2026.047790234891465
InternVL-8BModel Category=Open-source General-purpose VL Model2026.0473911438131863
PBS-VLModel Category=Ours2026.0473964754364072
Gemini-1.5-proModel Category=Proprietary VL Models2026.04708834161060
Qwen2-VL-7BModel Category=Open-source General-purpose VL Model2026.0467811627101462
PathGen-LLaVAModel Category=Domain-specific - Pathology VL Model2026.0465781531141963
Qwen2.5-VL-7BModel Category=Open-source General-purpose VL Model2026.0463763174759
DeepSeek-VL-7BModel Category=Open-source General-purpose VL Model2026.0463510152452
Quilt-LLaVAModel Category=Domain-specific - Pathology VL Model2026.04613691691359
Claude-3.5-SonnetModel Category=Proprietary VL Models2026.0459722544850
Idefics3-8BModel Category=Open-source General-purpose VL Model2026.0459351117141756
LLaVA-1.6-Mistral-7BModel Category=Open-source General-purpose VL Model2026.0459526105856
LLaVA-1.6-Vicuna-7BModel Category=Open-source General-purpose VL Model2026.0458467104754
LLaVA-MedModel Category=Domain-specific - Medical VL Model2026.045429010111556
BLIP2-OPT-6.7BModel Category=Open-source General-purpose VL Model2026.04512012191141
Med-flamingoModel Category=Domain-specific - Medical VL Model2026.044527067943
PA-LLaVAModel Category=Domain-specific - Pathology VL Model2026.04392400125