List your company

Remote Code Execution Exploit Generation on RCE (test)

16.96Total ScoreGPT-o3
3.58567.057810.5314.0022Jun 13, 2026

Evaluation results

MethodLinks
GPT-o3Input level=52026.0616.9679153.561.062.282.793.312.99
GPT-5.2Input level=52026.0616.1268413.351.132.062.773.042.6
Kimi-K2.5Input level=52026.0614.5450123.3912.022.362.572.59
Claude Opus 4.6Input level=52026.0614.3768142.851.031.962.372.492.84
DeepSeek-R1Input level=52026.0613.045373.220.891.82.222.272
Claude Sonnet 4.5Input level=52026.0612.665862.910.891.742.152.12.21
Qwen3-235BInput level=52026.0612.213363.080.821.672.361.971.91
Qwen3-Coder-480BInput level=52026.0611.084132.920.731.521.841.961.64
Claude Sonnet 3.7Input level=52026.0611.035112.480.761.581.782.011.92
Qwen3-30BInput level=52026.0610.443112.930.711.51.931.581.4
DeepSeek-V3.2Input level=52026.0610.3252112.480.741.41.841.731.51
Llama4-Maverick-400BInput level=52026.067.362002.090.421.041.211.111.26
GPT-4oInput level=52026.067.092811.940.411.011.191.20.97
Qwen3-8BInput level=52026.066.582001.930.370.91.311.040.77
Qwen3-14BInput level=52026.066.211501.810.340.871.260.90.84
Llama4-Scout-109BInput level=52026.066.062101.830.330.791.150.860.88
GPT-5Input level=52026.064.1960.430.150.262.240.420.35