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

General Question Answering on PopQA (Accuracy)

48.8Accuracy

SkillOrchestra+

10.73620.61830.540.382Feb 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
48.8
2026.02
42.6
2026.02
38.4
2026.02
36.6
2026.02
36.2
2026.02
35.4
2026.02
34
2026.02
32.4
2026.02
28.2
2026.02
28
2026.02
25.6
2026.02
23.2
2026.02
22.2
2026.02
22.2
2026.02
19.2
2026.02
16
2026.02
16
2026.02
12.2