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

Knowledge-intensive reasoning on C-Eval

90.2Score

Qwen3.5

82.077684.186386.29588.4037May 12, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
90.2
2026.05
88.2
2026.05
87.29
2026.05
85.89
2026.05
84.4
2026.05
83.88
2026.05
82.39