List your company

Causal-order reasoning on VCR-Causal

98.17AccuracyHuman Estimate
41.552456.251270.9585.6488Jun 1, 2025

Evaluation results

MethodLinks
Human Estimate2025.0698.17
LLaVA 1.6Model Category=Text-Generation Models2025.0657.24
Vicuna 1.5Model Category=Text-Generation Models2025.0656.03
RobustCLIPModel Category=Score-Based Models2025.0653.68
LLaVA 1.5Model Category=Text-Generation Models2025.0652.12
CLIP ViT L/14Model Category=Score-Based Models2025.0651.66
NegCLIPModel Category=Score-Based Models2025.0651.3
BLIP2 FEModel Category=Score-Based Models, Note=BLIP2 feature extractor model2025.0650.76
BLIP ITM BaseModel Category=Score-Based Models2025.0650.66
CLIP ViT B/32Model Category=Score-Based Models2025.0650.35
Random2025.0650
FLAVAModel Category=Score-Based Models2025.0649.99
BLIP2 ITMModel Category=Score-Based Models2025.0649.95
BLIP ITM LargeModel Category=Score-Based Models2025.0647.99
Qwen2.5-VLModel Category=Text-Generation Models2025.0647.26
Qwen3-VLModel Category=Text-Generation Models2025.0643.73