Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Specification Alignment on SPECBENCH
Loading...
96.8
Safety Score
GPT-5.4
76.832
82.016
87.2
92.384
Sep 18, 2025
Safety Score
Behavior Score
SAR Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Safety Score
Behavior Score
SAR Score
GPT-5.4
Model=GPT-5.4
2025.09
96.8
84.1
85.3
Gemini-3.1-pro
Model=Gemini-3.1-pro
2025.09
84.7
75.6
72.1
Kimi-K2.5
Model=Kimi-K2.5
2025.09
83.5
81.1
74.9
DeepSeek-V3.2
Model=DeepSeek-V3.2
2025.09
77.6
79
66.6
Feedback
Search any
task
Search any
task