List your company

Adversarial Code Compliance on C

100Decoupling ProbabilityLlama-3.1-8B
24.644.17563.7583.325Jan 29, 2026

Evaluation results

MethodLinks
Llama-3.1-8BModel Category=Open Source (Small), Strategy=RPA^C2026.0110052.7
DeepSeek-v3.2Model Category=Open Source (Large), Strategy=RPA^C2026.0197.545.9
Qwen3-235BModel Category=Open Source (Large), Strategy=RPA^C2026.0187.624.7
Gemma-3-27bModel Category=Open Source (Small), Strategy=RPA^C2026.0182.624.3
Gemini-2.5-FlashModel Category=Proprietary, Strategy=RPA^C2026.0179.835.2
GPT-5Model Category=Proprietary, Strategy=RPA^C2026.0173.226.5
Llama-3.2-3BModel Category=Open Source (Small), Strategy=RPA^C2026.0166.514.3
GPT-OSS-120BModel Category=Open Source (Large), Strategy=RPA^C2026.0138.52
GPT-5-MiniModel Category=Proprietary, Strategy=RPA^C2026.0127.50.6