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

Argument Quality Evaluation on WebisArgQuality 20

41.08F1 Score

Qwen3-4B-ArgumentOnly-Target-SFT

21.600826.657931.71536.7721Mar 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
41.08
2026.03
41.01
2026.03
39.37
2026.03
38.96
2026.03
38.58
2026.03
38
2026.03
37.77
2026.03
37.67
2026.03
36.43
2026.03
35.27
2026.03
34.97
2026.03
34.68
2026.03
33.82
2026.03
22.35