Vulnerability Attack Analysis on WebGenBench E-commerce target-domain and cross-domain 1.0
100Attack Success Rate (CodeQL)GPT-5.2
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT-5.2Evaluation Protocol=Held-out (target-domain)2026.02 | 100 | 100 | 100 | 86.67 | |
| Claude-4.5 OpusEvaluation Protocol=Held-out (target-domain)2026.02 | 100 | 100 | 100 | 100 | |
| Gemini-3 ProEvaluation Protocol=Held-out (target-domain)2026.02 | 100 | 100 | 100 | 100 | |
| Gemini-3 FlashEvaluation Protocol=Held-out (target-domain)2026.02 | 100 | 100 | 100 | 100 | |
| ComposerEvaluation Protocol=Held-out (target-domain)2026.02 | 100 | 100 | 100 | 100 | |
| GrokEvaluation Protocol=Held-out (target-domain)2026.02 | 100 | 100 | 100 | 81.82 | |
| GPT-5.2Evaluation Protocol=Cross-domain2026.02 | 76.47 | 81.25 | 74.23 | 70.97 | |
| Claude-4.5 OpusEvaluation Protocol=Cross-domain2026.02 | 72.73 | 81.25 | 72.73 | 80 | |
| ComposerEvaluation Protocol=Cross-domain2026.02 | 68.75 | 76.19 | 58.33 | 75 | |
| GrokEvaluation Protocol=Cross-domain2026.02 | 68.75 | 66.67 | 65 | 60.71 | |
| Gemini-3 ProEvaluation Protocol=Cross-domain2026.02 | 61.54 | 75 | 61.54 | 65.52 | |
| Gemini-3 FlashEvaluation Protocol=Cross-domain2026.02 | 50 | 66.67 | 50 | 56.25 |