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

General Language Modeling on CodaSet OOD Average (test)

87.84Performance (%)

Qwen3-235B

80.840882.657984.47586.2921May 25, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
87.846.4
87.597.1
876.8
2026.05
86.495
84.963.8
84.5214.9
2026.05
83.725.4
2026.05
83.673.3
2026.05
83.63.3
83.251.3
2026.05
82.774.2
82.474.9
2026.05
81.71.8
2026.05
81.531.4
81.421
81.112.2