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

Reasoning and Knowledge Assessment on Xstorycloze bo

72.96Accuracy

Ours-MoE-SFT

47.521654.125860.7367.3342Jul 12, 2025
Updated 20d ago

Evaluation Results

MethodLinks
2025.07
72.96
2025.07
61.86
2025.07
60.86
2025.07
60.8
2025.07
60.74
2025.07
60.6
2025.07
51.69
2025.07
50.43
2025.07
50.37
2025.07
49.97
2025.07
48.5