Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Attack Technique Extraction on CTIBench ATE
Loading...
69.6
Micro F1
GPT-4.1
-2.368
16.316
35
53.684
Jan 28, 2026
Micro F1
Updated 4d ago
Evaluation Results
Method
Method
Links
Micro F1
GPT-4.1
Model Group=frontier O...
2026.01
69.6
GPT-5-Mini
Model Group=frontier O...
2026.01
68.1
o3-Mini
Model Group=frontier O...
2026.01
59.9
GPT-5
Model Group=frontier O...
2026.01
57.8
Llama-3.3-70B-Instruct
Model Group=Llama-fami...
2026.01
51.9
Qwen-3-14B
Model Group=smaller sp...
2026.01
50.2
Foundation-Sec-8B-Reasoning
Model Group=our reason...
2026.01
49.1
GPT-OSS-20B
Model Group=GPT-OSS mo...
2026.01
47.8
GPT-5-Nano
Model Group=frontier O...
2026.01
45.3
Phi-4
Model Group=smaller sp...
2026.01
43.5
Qwen-3-8B
Model Group=smaller sp...
2026.01
40.8
Foundation-Sec-8B-Instruct
Model Group=Llama-fami...
2026.01
35.8
GPT-OSS-120B
Model Group=GPT-OSS mo...
2026.01
28.2
Llama-Primus-Nemotron-70B-Instruct
Model Group=Llama-fami...
2026.01
26.8
Llama-3.1-8B-Instruct
Model Group=Llama-fami...
2026.01
13.2
Llama-Primus-Merged
Model Group=Llama-fami...
2026.01
5.8
DeepHat-V1-7B
Model Group=smaller sp...
2026.01
0.4
Feedback
Search any
task
Search any
task