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

Reasoning Quality Assessment on SocialIQA

77.94AUROC

TRACED

28.820841.572954.32567.0771Mar 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
77.9473.7177.33-
2026.03
75.4--0.004
2026.03
75.3669.0965-
2026.03
74.8673.6277.42-
2026.03
73.8770.1378.46-
2026.03
72.1362.3370-
2026.03
71.9466.5853.75-
2026.03
71---
2026.03
70.9768.8370.91-
2026.03
70.8165.5777.5-
2026.03
70.862.1881.21-
2026.03
69.5768.9170.97-
2026.03
68.2164.4357.68-
2026.03
67.4164.4180.36-
2026.03
67.3860.184.88-
2026.03
66.7464.8583.93-
2026.03
66.461.7486.08-
2026.03
64.9261.1984.63-
2026.03
64.6563.3882.26-
2026.03
64.4865.2683.93-
2026.03
64.4562.2584.31-
2026.03
64.0760.6986.15-
2026.03
63.0458.876.79-
2026.03
62.3651.5684.37-
2026.03
62.3353.1683.24-
2026.03
61.5960.4887.5-
2026.03
59.2560.9581.94-
2026.03
59.1161.7480.65-
2026.03
58.7657.9681.54-
2026.03
58.6762.3791.94-
2026.03
49.3352.2987.44-
2026.03
48.2952.286.82-
2026.03
48.1751.6489.13-
2026.03
30.715085-