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

Complex reasoning on FEVER (test)

85.18Macro F1

EvoPool

0.118422.201744.28566.3683Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
85.18
2026.06
84.35
2026.06
83.6
2026.06
82.62
2026.06
82.36
2026.06
82.27
2026.06
81.32
2026.06
81.17
2026.06
79.88
2026.06
78.05
2026.06
77.67
2026.06
76.45
2026.06
76.26
2026.06
75.99
2026.06
75.99
2026.06
75.99
2026.06
75.99
2026.06
75.56
2026.06
74.28
2026.06
71.09
2026.06
70.99
2026.06
68.79
2026.06
64.77
2026.06
63.9
2026.06
62.83
2026.06
60.42
2026.06
50.83
2026.06
36.72
2026.06
35.41
2026.06
34.34
2026.06
32.85
2026.06
29.69
2026.06
16.67
2026.06
16.67
2026.06
16.67
2026.06
16.67
2026.06
3.39