List your company

Vulnerability Attack Analysis on WebGenBench Blogging target-domain and cross-domain 1.0

100ASR (CodeQL)Claude-4.5 Opus
40.574456.002271.4386.8578Feb 2, 2026

Evaluation results

MethodLinks
Claude-4.5 OpusEvaluation Protocol=Held-out (target-domain)2026.02100100100100
Gemini-3 FlashEvaluation Protocol=Held-out (target-domain)2026.02100100100100
GPT-5.2Evaluation Protocol=Cross-domain2026.0280.6587.577.9477.78
GPT-5.2Evaluation Protocol=Held-out (target-domain)2026.0280808065
Gemini-3 ProEvaluation Protocol=Held-out (target-domain)2026.0280808080
Claude-4.5 OpusEvaluation Protocol=Cross-domain2026.0276.9284.6276.9284
ComposerEvaluation Protocol=Cross-domain2026.0276.9281.8269.2381.25
GrokEvaluation Protocol=Held-out (target-domain)2026.0275607557.14
GrokEvaluation Protocol=Cross-domain2026.027577.7871.4366.67
Gemini-3 ProEvaluation Protocol=Cross-domain2026.0269.2381.2569.2372
ComposerEvaluation Protocol=Held-out (target-domain)2026.0266.67755075
Gemini-3 FlashEvaluation Protocol=Cross-domain2026.0242.8663.6442.8652