Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AQUA (ASR/HSR)
Loading...
94.4
Answer Selection Rate (ASR)
ShadowCoT
82.544
85.622
88.7
91.778
Apr 8, 2025
Answer Selection Rate (ASR)
Human Score Rate (HSR)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Answer Selection Rate (ASR)
Human Score Rate (HSR)
ShadowCoT
Target Model=Mistral
2025.04
94.4
89.7
DarkMind
Target Model=Mistral
2025.04
89.2
78.3
BadChain
Target Model=Mistral
2025.04
88.5
75.1
SABER
Target Model=Mistral
2025.04
83
71.6
Feedback
Search any
task
Search any
task