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

Holistic Evaluation on CodaSet ID Average (test)

90.6Accuracy

Qwen3-235B-A22B

71.661676.578381.49586.4117May 25, 2026
Updated 8d ago

Evaluation Results

MethodLinks
90.65
89.745.2
2026.05
89.352.1
2026.05
89.131.9
88.712.7
88.513.9
87.9411.9
2026.05
87.57.8
2026.05
86.84.2
2026.05
86.774.2
2026.05
86.62
84.184.4
83.792.4
82.831
2026.05
82.232.3
72.391.8