Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Utility Evaluation on Utility Benchmark
Loading...
8.08
Utility Score
SFT
6.9152
7.2176
7.52
7.8224
Oct 17, 2025
Utility Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Utility Score
SFT
Model=Qwen2.5-7B-Instruct
2025.10
8.08
HarmRLVR
Model=Qwen2.5-7B-Instruct
2025.10
8.05
SFT
Model=Qwen3-8B
2025.10
8.02
Base
Model=Qwen2.5-7B-Instruct
2025.10
7.98
Base
Model=Qwen3-8B
2025.10
7.89
HarmRLVR
Model=Qwen3-8B
2025.10
7.81
SFT
Model=Llama-3.1-8B-Ins...
2025.10
7.79
HarmRLVR
Model=Llama-3-8B-Instruct
2025.10
7.73
Base
Model=Llama-3.1-8B-Ins...
2025.10
7.73
HarmRLVR
Model=Llama-3.1-8B-Ins...
2025.10
7.71
Base
Model=Llama-3-8B-Instruct
2025.10
7.48
SFT
Model=Llama-3-8B-Instruct
2025.10
7.44
HarmRLVR
Model=DeepSeek-R1-Dist...
2025.10
7.3
Base
Model=DeepSeek-R1-Dist...
2025.10
7.22
SFT
Model=DeepSeek-R1-Dist...
2025.10
6.96
Feedback
Search any
task
Search any
task
