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

Long-form Question Answering on Biography MixP (50% polluted)

70.11VeriScore F1@k

MIRAGE

13.076427.883242.6957.4968Jul 6, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
70.11
2026.07
61.25
2026.07
58.99
2026.07
58.39
2026.07
56.55
2026.07
56.37
2026.07
56.23
2026.07
53.75
2026.07
52.58
2026.07
51.58
2026.07
49.5
2026.07
48.91
2026.07
48.76
2026.07
48.14
2026.07
48.03
2026.07
42.56
2026.07
40.47
2026.07
36.77
2026.07
35.18
2026.07
34.03
2026.07
33.64
2026.07
33.36
2026.07
31.44
2026.07
28.86
2026.07
26.64
2026.07
15.27