Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Cybersecurity Knowledge Evaluation on CyMtc (500)
Loading...
95.6
CyMtc (500) Score
GPT-5
63.984
72.192
80.4
88.608
Jan 29, 2026
CyMtc (500) Score
Updated 4d ago
Evaluation Results
Method
Method
Links
CyMtc (500) Score
GPT-5
evaluation_context=Lar...
2026.01
95.6
RedSage-8B-CFW
evaluation_context=Bas...
2026.01
93.8
RedSage-8B-Base
evaluation_context=Bas...
2026.01
92.6
RedSage-8B-Seed
evaluation_context=Bas...
2026.01
92.2
Qwen3-8B-Base
evaluation_context=Bas...
2026.01
92
Qwen3-32B
evaluation_context=Lar...
2026.01
91.8
RedSage-8B-DPO
evaluation_context=Ins...
2026.01
90
RedSage-8B-Ins
evaluation_context=Ins...
2026.01
89.8
Qwen3-8B
evaluation_context=Ins...
2026.01
88.6
Foundation-Sec-8B
evaluation_context=Bas...
2026.01
86.6
DeepHat-V1-7B
evaluation_context=Ins...
2026.01
86
Llama-3.1-8B
evaluation_context=Bas...
2026.01
84.2
Llama-Primus-Merged
evaluation_context=Ins...
2026.01
83.8
Llama-Primus-Base
evaluation_context=Ins...
2026.01
83.8
Foundation-Sec-8B-Instruct
evaluation_context=Ins...
2026.01
83
Llama-3.1-8B-Instruct
evaluation_context=Ins...
2026.01
82.8
Lily-Cybersecurity-7B-v0.2
evaluation_context=Ins...
2026.01
65.2
Feedback
Search any
task
Search any
task