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

General Question Answering on NQ (Exact Match)

54.8Exact Match (EM)

SkillOrchestra+

5.29618.1483143.852Jan 17, 2026Jan 31, 2026Feb 15, 2026Mar 2, 2026Mar 16, 2026Mar 31, 2026Apr 15, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.02
54.8
2026.02
54.2
2026.04
43
2026.01
42.43
2026.01
42.18
2026.04
42.1
2026.04
41.8
2026.01
41.46
2026.01
41.32
2026.04
41.3
2026.01
40.94
2026.01
40.6
2026.04
40.4
2026.01
40.36
2026.04
39.9
2026.01
39.63
2026.04
39.5
2026.01
39.39
2026.04
39
2026.04
38.9
2026.01
38.8
2026.02
38.8
2026.04
38.1
2026.01
36.34
2026.01
36.34
2026.04
35.7
2026.04
35.2
2026.01
34.62
2026.01
33.71
2026.01
33.65
2026.01
33.62
2026.01
32.82
2026.02
32.8
2026.01
32.38
2026.04
30.3
2026.02
30
2026.02
29.8
2026.02
29.6
2026.02
27.8
2026.02
27.6
2026.02
26.5
2026.02
26.2
2026.02
25.8
2026.02
25.2
2026.02
23.6
2026.02
23
2026.02
21.2
2026.04
18.4
2026.04
15.9
2026.02
12.6
2026.02
9.2
2026.04
7.2