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

General Question Answering on TriviaQA (Exact Match)

69.02Exact Match

Agentic-R

0.567218.338636.1153.8814Jan 17, 2026Jan 30, 2026Feb 13, 2026Feb 26, 2026Mar 12, 2026Mar 25, 2026Apr 8, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.01
69.02
2026.01
68.7
2026.01
65.78
2026.01
65.61
2026.01
65.5
2026.01
65.5
2026.01
64.9
2026.01
64.72
2026.01
63.66
2026.01
63.59
2026.01
63.46
2026.01
62.52
2026.01
62.48
2026.01
62.39
2026.01
62.33
2026.01
61
2026.01
60.81
2026.01
60.73
2026.04
59.7
2026.04
59.7
2026.04
59.7
2026.01
59.59
2026.01
59.2
2026.01
58.69
2026.01
58.5
2026.04
58.3
2026.01
57.64
2026.01
57.4
2026.04
57.4
2026.01
57.19
2026.04
56.5
2026.01
56.29
2026.04
56
2026.04
55.8
2026.01
54.5
2026.01
54.4
2026.04
54.4
2026.04
54.1
2026.01
53.7
2026.01
48.8
2026.01
47.8
2026.01
47.2
2026.04
47.2
2026.04
45.5
2026.01
44.9
2026.01
44.3
2026.01
40.8
2026.01
35.4
2026.01
31.2
2026.01
29.2
2026.04
29.2
2026.01
28.8
2026.04
28.8
2026.04
3.2