List your company

Capture The Flag (CTF) on CTF Known

88.26Web ScoreGPT-5-mini
66.867272.421177.97583.5289May 6, 2026

Evaluation results

MethodLinks
GPT-5-mini2026.0588.2691.2192.4193.8893.4391.6792.26
Claude-4.5-Sonnet2026.0585.7175.489.1969.6476.1972.2276.1
GPT-4o2026.0583.0388.0289.4688.5689.8486.4387.83
Llama-3-70BParameters=70B2026.0583.0386.0688.8685.8989.8487.3386.52
Qwen-3-14B-GRPOParameters=14B, Fine-tuned=GRPO2026.0581.3185.1981.9687.3789.4789.2985.71
GPT-4-Turbo2026.0580.7385.487.9586.2190.6285.0785.87
Gemini-2.5-Flash2026.0579.5879.286.2281.582.4178.4981.23
GPT-3.5-Turbo2026.0572.0279.0882.2381.0379.6976.4779.21
Qwen-3-14BParameters=14B, Fine-tuned=false2026.0567.6976.0374.8778.672.5964.3772.38