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

Social Interaction Question Answering on SocialIQA (test)

75.49Accuracy

TaT

48.148455.246762.34569.4433Mar 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
75.49
2026.03
69.7
2026.03
69.33
2026.03
67.7
2026.03
67.69
2026.03
66.6
2026.03
66.38
2026.03
66.17
2026.03
65.47
2026.03
65.47
2026.03
65.2
2026.03
61.21
2026.03
60.85
2026.03
60.39
2026.03
60.18
2026.03
55.27
2026.03
50.2
2026.03
49.2