List your company

Pentesting Strategy Generation on Pentesting Scenarios (test)

73Strategy Success RateQwen-3-14B-GRPO
34.5244.5154.564.49May 6, 2026

Evaluation results

MethodLinks
Qwen-3-14B-GRPOParameters=14B, Optimization=GRPO2026.0573
Claude 4.5 Sonnet2026.0565
GPT-52026.0562
GPT 4.12026.0560
Claude 3 Haiku2026.0554
GPT-4o-mini2026.0552
Gemini 2.5 Flash2026.0545
Gemini 2.0 Flash2026.0540
LLaMA-3.1-8BParameters=8B2026.0540
Qwen-3-14BParameters=14B2026.0539
GPT-3.5-turbo2026.0536