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

Public Information Retention on PopQA D_special (test)

48.25r_pub Score

gpt-each

0.077212.583625.0937.5964Apr 14, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.04
48.25
2025.04
47.93
45.53
43.84
2025.04
40.4
2025.04
23.86
2025.04
7.26
2025.04
6.74
2025.04
5.9
2025.04
1.93