Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Chinese Language Evaluation on C-Eval (val)
Loading...
83
C-Eval 0-shot Score
AquilaChat2
25.696
40.573
55.45
70.327
Mar 7, 2024
C-Eval 0-shot Score
C-Eval 5-shot Score
Updated 4d ago
Evaluation Results
Method
Method
Links
C-Eval 0-shot Score
C-Eval 5-shot Score
AquilaChat2
Size=34B
2024.03
83
89.4
Yi-Chat
Size=34B
2024.03
77
78.5
Yi-Chat-8bits(GPTQ)
Size=34B
2024.03
76.8
79
Yi-Chat-4bits(AWQ)
Size=34B
2024.03
75.7
77.3
Yi-Chat-8bits(GPTQ)
Size=6B
2024.03
69.2
73.9
Yi-Chat
Size=6B
2024.03
68.8
74.2
Yi-Chat-4bits(AWQ)
Size=6B
2024.03
67.5
72.3
Qwen-Chat
Size=14B
2024.03
66.1
70.1
Baichuan2-Chat
Size=13B
2024.03
56
54.8
InternLM-Chat
Size=20B
2024.03
51.2
53.6
LLaMA2-Chat
Size=70B
2024.03
35
41.3
LLaMA2-Chat
Size=13B
2024.03
27.9
35.9
Feedback
Search any
task
Search any
task