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

High-stakes specialized classification on ChemProt (test)

59.09Macro F1

EvoPool

18.072428.721239.3750.0188Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
59.09
2026.06
59.09
2026.06
58.26
2026.06
55.57
2026.06
55.57
2026.06
55.35
2026.06
54.32
2026.06
54.32
2026.06
53.96
2026.06
53.96
2026.06
53.94
2026.06
53.94
2026.06
53.83
2026.06
53.83
2026.06
51.94
2026.06
51.92
2026.06
51.7
2026.06
51.7
2026.06
47.18
2026.06
46.79
2026.06
46.79
2026.06
43.66
2026.06
40.82
2026.06
39.93
2026.06
38.77
2026.06
38.03
2026.06
37.25
2026.06
32.62
2026.06
32.53
2026.06
31.78
2026.06
31.77
2026.06
30.49
2026.06
29.45
2026.06
28.4
2026.06
28.17
2026.06
28.17
2026.06
28.17
2026.06
28.17
2026.06
28.09
2026.06
27.75
2026.06
25.76
2026.06
22.67
2026.06
22.04
2026.06
21.94
2026.06
21.93
2026.06
21.29
2026.06
20.84
2026.06
19.94
2026.06
19.65