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

Comprehensive Chinese Evaluation on C-Eval

89Accuracy

Qwen3

42.77254.773566.77578.7765Sep 5, 2025Oct 4, 2025Nov 3, 2025Dec 3, 2025Jan 1, 2026Jan 31, 2026Mar 2, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.03
89
2026.03
88.34
2026.03
87.84
2026.03
87.67
2026.03
87.64
2026.03
87.35
2026.03
87.12
2026.03
86.97
2026.03
86.79
2026.03
86.18
2026.03
85.93
2026.03
85.65
2025.09
81.68
2025.09
78.89
2025.12
69
2025.12
67.5
2025.09
61.02
2025.09
54.39
2026.03
50.16
2025.09
49.26
2025.09
48.94
2026.03
44.55