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

Single-hop Question Answering on TriviaQA (test)

66Accuracy

GIGPO w/ PaW

16.629.42542.2555.075Jan 31, 2026Feb 26, 2026Mar 24, 2026Apr 19, 2026May 15, 2026Jun 10, 2026Jul 6, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.06
66
2026.07
66
2026.06
64.9
2026.07
64.7
2026.06
64.4
2026.06
63.9
2026.01
63.4
2026.02
62.4
2026.02
62
2026.06
61.8
2026.06
61.8
2026.07
61.8
2026.02
61.6
2026.01
61.4
2026.06
61.2
2026.06
61
2026.07
61
2026.06
60.9
2026.01
60.8
2026.07
60.7
2026.02
59.7
2026.02
59.7
2026.02
59.7
2026.02
59.7
2026.07
59.5
2026.01
59
2026.06
58.5
2026.02
58.3
2026.01
58
2026.01
57.8
2026.06
57.4
2026.07
57.4
2026.02
57.1
2026.01
56.8
2026.01
56.6
2026.02
56.5
2026.01
55.6
2026.06
54.5
2026.07
54.5
2026.01
54.4
2026.02
54.4
2026.07
53.7
2026.01
52.2
2026.01
50.4
2026.01
47.2
2026.02
47.2
2026.01
45.5
2026.02
45.5
2026.01
44.9
2026.02
44.9
2026.07
44.9
2026.01
44.6
2026.01
42.8
2026.01
31.2
2026.02
31.2
2026.01
29.2
2026.02
29.2
2026.01
28.8
2026.02
28.8
2026.01
18.5