List your company
ResearchFormerly WizWand

Direct-answer Visual Question Answering on A-OKVQA

68.7AccuracyMC-CoT_Base
21.827233.996146.16558.3339Nov 23, 2023Apr 5, 2024Aug 17, 2024Dec 29, 2024May 12, 2025Sep 23, 2025Feb 4, 2026
Updated 8mo ago

Evaluation results

MethodLinks
MC-CoT_BaseVision Model=DETR [11], Text Model=UnifiedQABase [24], Parameters=223M2023.1168.7
LASERModel=Qwen-VL, Decoding=LASER2026.0262.82
VCDModel=Qwen-VL, Decoding=VCD2026.0261.34
ViCropModel=Qwen-VL, Decoding=ViCrop2026.0260.12
SampleModel=Qwen-VL, Decoding=Sample2026.0259.64
BLIP-2Vision Model=CLIP-VIT-LARGE [41], Text Model=FlanT5XXL [15], Parameters=11B2023.1153.2
GPV-2Vision Model=VinVL [59], Text Model=T5-Base [42], Parameters=300M2023.1148.6
IPVRVision Model=Faster-RCNN [44], Text Model=OPT [62], Parameters=66B2023.1146.4
PICaVision Model=VinVL [59], Text Model=GPT-3 [10], Parameters=175B2023.1142.4
PaLM-COTText Model=PaLM [13], Parameters=540B2023.1141.5
KRISPVision Model=Faster R-CNN [44], Text Model=BERT [23], Parameters=200M2023.1133.7
LXMERTVision Model=Transformer [49], Text Model=Transformer [49], Parameters=220M2023.1130.7
VILBERTVision Model=Faster R-CNN [44], Text Model=BERT [23], Parameters=300M2023.1130.6
LASERModel=LLaVA-1.5, Decoding=LASER2026.0228.18
VCDModel=LLaVA-1.5, Decoding=VCD2026.0225.54
PythiaVision Model=ResNet [19], Text Model=BERT [23], Parameters=70M2023.1125.2
ViCropModel=LLaVA-1.5, Decoding=ViCrop2026.0223.95
SampleModel=LLaVA-1.5, Decoding=Sample2026.0223.63