Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Algebraic Reasoning on AQUA (PPL)
Loading...
22.7
PPL
ShadowCoT
22.02
26.61
31.2
35.79
Apr 8, 2025
PPL
Updated 1mo ago
Evaluation Results
Method
Method
Links
PPL
ShadowCoT
Target Model=Mistral-7B
2025.04
22.7
DarkMind
Target Model=Mistral-7B
2025.04
31.9
BadChain
Target Model=Mistral-7B
2025.04
39.7
Feedback
Search any
task
Search any
task