Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Trustworthiness Evaluation on Adv Fact (human evaluation)
Loading...
68
Control Wins
Sparse Activation Control
64.6
66.3
68
69.7
Nov 4, 2024
Control Wins
Tie Count
No Control Wins
Updated 1mo ago
Evaluation Results
Method
Method
Links
Control Wins
Tie Count
No Control Wins
Sparse Activation Control
2024.11
68
26
6
Feedback
Search any
task
Search any
task
