List your company

Counterfactual Reasoning on CVQA

71.41AccuracyBlind-VLM
26.263637.984349.70561.4257Feb 7, 2026

Evaluation results

MethodLinks
Blind-VLMLLM=Phi2, Evaluation Mode=Boolean2026.0271.41
StableLSDLLM=Phi2, Evaluation Mode=Boolean2026.0270.44
SPOTLLM=Phi2, Evaluation Mode=Boolean2026.0269.47
DINOSAURLLM=Phi2, Evaluation Mode=Boolean2026.0269.29
FT-DINOSAURLLM=Phi2, Evaluation Mode=Boolean2026.0268.85
Slot DiffusionLLM=Phi2, Evaluation Mode=Boolean2026.0268.23
mFRESALLM=Phi2, Evaluation Mode=Boolean2026.0266.64
VQDINOMLPLLM=Phi2, Evaluation Mode=Boolean2026.0266.37
DINOSAURv2LLM=Phi2, Evaluation Mode=Boolean2026.0265.75
Blind-VLMLLM=Qwen2-7B, Evaluation Mode=Boolean2026.0265.57
DINOSAURv2LLM=Qwen2-7B, Evaluation Mode=Boolean2026.0264.07
DINOv2LLM=Phi2, Evaluation Mode=Boolean2026.0263.72
DINOSAURLLM=Qwen2-7B, Evaluation Mode=Boolean2026.0263.72
StableLSDLLM=Qwen2-7B, Evaluation Mode=Boolean2026.0262.39
mFRESALLM=Qwen2-7B, Evaluation Mode=Boolean2026.0260.44
Slot DiffusionLLM=Qwen2-7B, Evaluation Mode=Boolean2026.0259.56
SPOTLLM=Qwen2-7B, Evaluation Mode=Boolean2026.0257.61
FT-DINOSAURLLM=Qwen2-7B, Evaluation Mode=Boolean2026.0257.17
VQDINOMLPLLM=Qwen2-7B, Evaluation Mode=Boolean2026.0255.66
DINOv2LLM=Qwen2-7B, Evaluation Mode=Boolean2026.0253.54
DINOv2LLM=Qwen2-7B, Evaluation Mode=Direct2026.0245.74
VQDINOMLPLLM=Qwen2-7B, Evaluation Mode=Direct2026.0242.34
DINOSAURv2LLM=Qwen2-7B, Evaluation Mode=Direct2026.0242.09
FT-DINOSAURLLM=Qwen2-7B, Evaluation Mode=Direct2026.0242
SPOTLLM=Qwen2-7B, Evaluation Mode=Direct2026.0241.83
mFRESALLM=Qwen2-7B, Evaluation Mode=Direct2026.0241.39
DINOSAURLLM=Qwen2-7B, Evaluation Mode=Direct2026.0241.13
StableLSDLLM=Qwen2-7B, Evaluation Mode=Direct2026.0241.04
Slot DiffusionLLM=Qwen2-7B, Evaluation Mode=Direct2026.0239.39
FT-DINOSAURLLM=Phi2, Evaluation Mode=Direct2026.0239.13
StableLSDLLM=Phi2, Evaluation Mode=Direct2026.0238.26
mFRESALLM=Phi2, Evaluation Mode=Direct2026.0238.09
DINOv2LLM=Phi2, Evaluation Mode=Direct2026.0236.96
SPOTLLM=Phi2, Evaluation Mode=Direct2026.0236.35
DINOSAURLLM=Phi2, Evaluation Mode=Direct2026.0235.74
VQDINOMLPLLM=Phi2, Evaluation Mode=Direct2026.0235.13
DINOSAURv2LLM=Phi2, Evaluation Mode=Direct2026.0234.52
Slot DiffusionLLM=Phi2, Evaluation Mode=Direct2026.0233.83
Blind-VLMLLM=Qwen2-7B, Evaluation Mode=Direct2026.0232.69
Blind-VLMLLM=Phi2, Evaluation Mode=Direct2026.0228