Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Knowledge Evaluation on Natural Questions (NQ) (Evaluation)

59.4Accuracy

GPT-4o

3.55218.05132.5547.049Jan 7, 2026Jan 11, 2026Jan 15, 2026Jan 19, 2026Jan 23, 2026Jan 27, 2026Jan 31, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
59.4
2026.01
59.3
2026.01
59.2
2026.01
54.5
2026.01
44.1
2026.01
43.8
2026.01
43.8
2026.01
41.2
2026.01
40.1
2026.01
38.9
2026.01
38.9
2026.01
37.3
2026.01
32.1
2026.01
29.2
2026.01
27.3
2026.01
25.3
2026.01
6.7
2026.01
6.7
2026.01
6.6
2026.01
6.6
2026.01
6.3
2026.01
5.7