Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Comprehensive Chinese Evaluation on C-Eval
Loading...
89
Accuracy
Qwen3
42.772
54.7735
66.775
78.7765
Dec 29, 2025
Jan 8, 2026
Jan 19, 2026
Jan 29, 2026
Feb 9, 2026
Feb 19, 2026
Mar 2, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3
Model=Qwen3, Number of...
2026.03
89
R1-Distill
Model=R1-Distill, Numb...
2026.03
88.34
AloePri
Model=R1-Distill, Numb...
2026.03
87.84
DS-V3.1-Terminus (no_think)
Model=DS-V3.1-Terminus...
2026.03
87.67
AloePri
Model=Qwen3, Number of...
2026.03
87.64
Qwen3
Model=Qwen3, Number of...
2026.03
87.35
AloePri
Model=Qwen3, Number of...
2026.03
87.12
Qwen3-MoE-Instruct
Model=Qwen3-MoE-Instru...
2026.03
86.97
AloePri
Model=Qwen3-MoE-Instru...
2026.03
86.79
R1-Distill
Model=R1-Distill, Numb...
2026.03
86.18
AloePri
Model=R1-Distill, Numb...
2026.03
85.93
AloePri
Model=DS-V3.1-Terminus...
2026.03
85.65
MoE + L_ERC
Number of Parameters=1...
2025.12
69
MoE
Number of Parameters=1...
2025.12
67.5
Llama3
Model=Llama3, Number o...
2026.03
50.16
AloePri
Model=Llama3, Number o...
2026.03
44.55
Feedback
Search any
task
Search any
task