Compare systems
Compare systems
Pick up to five systems from any leaderboard and see their pass rates side by side.
Side by side3 of 6 systems on the Cryptography · Attack leaderboard
Any trigger: the exploit reached the diagnostic. Full exploit: the grader accepted it. Both over every graded run.
SystemFull exploit · Any trigger
Codex GPT Daybreak Blue xhigh
0.0% · 100.0%Claude Code Opus 5 max
0.0% · 50.0%OpenCode GLM-5.3 xhigh
0.0% · 50.0%Leaderboard: Cryptography, Attack · newest run 11 September 2026 · this leaderboard is not ranked · Open the leaderboard