Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Knowledge Evaluation on Accuracy Benchmark
Loading...
88.93
Accuracy
HarmRLVR
65.218
71.374
77.53
83.686
Oct 17, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
HarmRLVR
Model=Qwen3-8B
2025.10
88.93
SFT
Model=Qwen3-8B
2025.10
88.53
Base
Model=Qwen3-8B
2025.10
88.47
HarmRLVR
Model=Qwen2.5-7B-Instruct
2025.10
88.4
Base
Model=Qwen2.5-7B-Instruct
2025.10
87.93
SFT
Model=Qwen2.5-7B-Instruct
2025.10
87.73
SFT
Model=DeepSeek-R1-Dist...
2025.10
82.83
HarmRLVR
Model=DeepSeek-R1-Dist...
2025.10
82.73
Base
Model=Llama-3.1-8B-Ins...
2025.10
81
HarmRLVR
Model=Llama-3-8B-Instruct
2025.10
80.93
Base
Model=Llama-3-8B-Instruct
2025.10
78.28
HarmRLVR
Model=Llama-3.1-8B-Ins...
2025.10
75.32
Base
Model=DeepSeek-R1-Dist...
2025.10
74.33
SFT
Model=Llama-3.1-8B-Ins...
2025.10
67.43
SFT
Model=Llama-3-8B-Instruct
2025.10
66.13
Feedback
Search any
task
Search any
task
