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

Question Answering on PopQA (Score)

43.93Score

CDKC (w/ 2 round)

11.554819.959928.36536.7701Dec 15, 2025Dec 25, 2025Jan 4, 2026Jan 14, 2026Jan 24, 2026Feb 3, 2026Feb 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
43.93
2026.02
43.44
2026.02
42.73
2026.02
40.33
2026.02
37.33
2025.12
37
2026.02
35
2025.12
33.1
2025.12
32.2
2025.12
32.2
2025.12
31.9
2026.02
31.67
2025.12
30.9
2025.12
30.7
2026.02
29.43
29.3
2026.02
28.97
2025.12
28.9
2026.02
28.27
2026.02
28.1
2026.02
26.97
2025.12
26.7
2026.02
26.6
2025.12
26.5
2025.12
25.5
2025.12
25.5
2026.02
25.07
2025.12
24.7
2026.02
24.33
2025.12
24.3
2025.12
23.7
2025.12
21.5
2026.02
20.97
2025.12
20.8
2025.12
20.7
2025.12
20.4
2026.02
20.33
18
17.9
2026.02
16.57
2026.02
16.53
2025.12
16.5
2026.02
16.13
2026.02
15.9
2026.02
15.43
2026.02
15.07
14.5
2026.02
14.5
2025.12
14.1
12.8