Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Steering Success Rate on PopQA 150 questions
Loading...
33
Base SR
DeepSeek 7B
13.344
18.447
23.55
28.653
Nov 26, 2025
Base SR
Adapted SR
Delta SR
Updated 2mo ago
Evaluation Results
Method
Method
Links
Base SR
Adapted SR
Delta SR
DeepSeek 7B
Model=DeepSeek 7B
2025.11
33
45.6
12.6
Llama 3 8B
Model=Llama 3 8B
2025.11
33
42.6
9.6
Qwen 2.5 7B
Model=Qwen 2.5 7B
2025.11
24.2
28.6
4.3
Qwen 2.5 32B
Model=Qwen 2.5 32B
2025.11
21.2
34.8
13.6
Gemma 2 9B
Model=Gemma 2 9B
2025.11
14.1
39.6
25.4
Feedback
Search any
task
Search any
task