List your company

Vulnerability Attack Analysis on WebGenBench Internal Tools 1.0

90ASR (CodeQL)Claude-4.5 Opus
22.439.9557.575.05Feb 2, 2026

Evaluation results

MethodLinks
Claude-4.5 OpusEvaluation Protocol=Cross-domain2026.029093.759093.33
GPT-5.2Evaluation Protocol=Cross-domain2026.0288.2487.583.8275
GrokEvaluation Protocol=Cross-domain2026.028578.578168.18
ComposerEvaluation Protocol=Cross-domain2026.0283.3387.571.4387.5
Gemini-3 ProEvaluation Protocol=Cross-domain2026.0280.7787.580.7783.33
Gemini-3 FlashEvaluation Protocol=Cross-domain2026.0280758075
GPT-5.2Evaluation Protocol=Held-out (target-domain)2026.0260756075
Claude-4.5 OpusEvaluation Protocol=Held-out (target-domain)2026.0250605060
ComposerEvaluation Protocol=Held-out (target-domain)2026.0250605057.14
Gemini-3 ProEvaluation Protocol=Held-out (target-domain)2026.0240604044
GrokEvaluation Protocol=Held-out (target-domain)2026.0233.335033.3350
Gemini-3 FlashEvaluation Protocol=Held-out (target-domain)2026.0225602535