Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM steering evaluation on DebateMix
Loading...
0.51
LLM Judge Score
K-Steering
0.094
0.202
0.31
0.418
May 30, 2025
LLM Judge Score
Agreement Rate
Updated 12d ago
Evaluation Results
Method
Method
Links
LLM Judge Score
Agreement Rate
K-Steering
Model=Olmo-2-7B, K=1
2025.05
0.51
-
CAA
Model=Llama-3.2-3B, K=1
2025.05
0.38
-
K-Steering
Model=Llama-3.2-3B, K=1
2025.05
0.37
-
CAA
Model=Olmo-2-7B, K=1
2025.05
0.36
-
CAA
Model=Llama-3.2-3B, K=3
2025.05
0.34
-
K-Steering
Model=Llama-3.2-3B, K=2
2025.05
0.33
-
CAA
Model=Llama-3.2-3B, K=2
2025.05
0.32
-
K-Steering
Model=Olmo-2-7B, K=3
2025.05
0.3
-
K-Steering
Model=Olmo-2-7B, K=2
2025.05
0.28
-
K-Steering
Model=Llama-3.2-3B, K=3
2025.05
0.26
-
CAA
Model=Olmo-2-7B, K=2
2025.05
0.25
-
CAA
Model=Olmo-2-7B, K=3
2025.05
0.11
-
Feedback
Search any
task
Search any
task