Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Paired-prompt evaluation on SugarCrepe

64.56Simple Accuracy

LLaVA-NeXT-Vicuna-7B

61.762462.488763.21563.9413Jan 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
64.5629.2383.24
2026.01
61.8723.8586.81