List your company

Safe Code Generation on Java Safe Code Generation Dataset

97.18Safe Code RateClaude Sonnet 4.6
18.08838.621559.15579.6885Jun 15, 2026

Evaluation results

MethodLinks
Claude Sonnet 4.6Prompting Condition=+Comp. I (SPARK Component I)2026.0697.18
Claude Sonnet 4.6Prompting Condition=Baseline2026.0694.37
GPT-5.4Prompting Condition=+Comp. I (SPARK Component I)2026.0693.66
Claude Haiku 4.5Prompting Condition=+Comp. I (SPARK Component I)2026.0690.85
GPT-5.5Prompting Condition=+Comp. I (SPARK Component I)2026.0689.84
Claude Haiku 4.5Prompting Condition=Baseline2026.0688.73
GPT-5.5Prompting Condition=Baseline2026.0685.71
DeepSeek V4 ProPrompting Condition=+Comp. I (SPARK Component I)2026.0683.1
GPT-5.4-miniPrompting Condition=+Comp. I (SPARK Component I)2026.0683.1
GPT-5.4Prompting Condition=Baseline2026.0679.58
DeepSeek V4 FlashPrompting Condition=+Comp. I (SPARK Component I)2026.0676.76
GPT-5.4-miniPrompting Condition=Baseline2026.0669.72
DeepSeek V4 ProPrompting Condition=Baseline2026.0658.45
DeepSeek V4 FlashPrompting Condition=Baseline2026.0648.59
Claude Haiku 4.5Prompting Condition=Plain2026.0636.62
GPT-5.4Prompting Condition=Plain2026.0635.92
GPT-5.5Prompting Condition=Plain2026.0631.69
Claude Sonnet 4.6Prompting Condition=Plain2026.0630.99
GPT-5.4-miniPrompting Condition=Plain2026.0628.17
DeepSeek V4 ProPrompting Condition=Plain2026.0625.35
DeepSeek V4 FlashPrompting Condition=Plain2026.0621.13