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

Argument Classification on UKP (Accuracy)

82.1Accuracy

gpt-oss-120b

24.3839.36554.3569.335Feb 25, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.02
82.1
2026.02
80.4
2026.02
79.7
2026.02
78.7
2026.02
78.6
2026.02
78
2026.02
77.2
2026.02
76.9
2026.02
76.8
2026.02
76.1
2026.02
75.9
2026.02
75.6
2026.02
75.3
2026.02
75
2026.02
73.1
2026.02
72.5
2026.02
71.4
2026.02
70.9
2026.02
65.4
2026.02
65.4
2026.02
61.7
2026.02
55.4
2026.02
53.5
2026.02
42.2
2026.02
37.3
2026.02
26.6