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

Social Reasoning on Sotopia (all)

2.73Rel Score

FT+MS

0.17160.83581.52.1642Sep 26, 2025
Updated 5d ago

Evaluation Results

MethodLinks
2025.09
2.734.47.464.86
2025.09
2.74.777.675.05
2025.09
2.474.457.34.74
2025.09
2.424.787.434.88
2025.09
2.373.816.694.29
2025.09
2.375.617.485.15
2025.09
2.184.226.844.41
2025.09
2.074.547.264.62
2025.09
1.924.016.64.18
2025.09
1.543.485.933.65
2025.09
1.494.76.464.22
2025.09
1.285.186.884.45
2025.09
1.25.376.674.41
2025.09
0.973.295.253.17
2025.09
0.275.096.113.82