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

Complex Reasoning on SciFact (test)

76.17Macro-F1

LLM annotation

17.753232.919148.08563.2509Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
76.17
2026.06
76.17
2026.06
76.17
2026.06
76.17
2026.06
59.19
2026.06
58.9
2026.06
51.34
2026.06
50.88
2026.06
47.88
2026.06
46.97
2026.06
46.47
2026.06
44.42
2026.06
43.55
2026.06
42.05
2026.06
40.96
2026.06
40.6
2026.06
38.71
2026.06
37.97
2026.06
36.09
2026.06
35.53
2026.06
32.48
2026.06
31.59
2026.06
31.11
2026.06
29.81
2026.06
29.29
2026.06
29.03
2026.06
29.01
2026.06
28.9
2026.06
28.64
2026.06
28.55
2026.06
27.59
2026.06
27.43
2026.06
26.13
2026.06
21.12
2026.06
20.51
2026.06
20.51
2026.06
20