ResearchBenchmarksVulnerability Exploitation on XBOW (full)Follow7.73Total CostAWE7.18410.869514.55518.2405Mar 1, 2026Evaluation ResultsMethodMethodLinksTotal CostCost per SolveTotal Tokens UsedTokens per SolveAWE2026.037.730.1131,120,00020,700MAPTA2026.0321.380.26754,870,000685,900