Compare systems
Compare systems
Pick up to five systems from any leaderboard and see their pass rates side by side.
Side by side3 of 9 systems on the Unpatched · Defend leaderboard
Any credit: partial or full credit. Full fix: full credit. Both over every graded run.
SystemFull fix · Any credit
Codex GPT-6 Astra xhigh
35.3% · 41.2%Claude Code Fable 5.1 high
28.6% · 42.9%Codex GPT-5.6 Sol xhigh
16.7% · 29.2%Leaderboard: Unpatched, Defend · newest run 10 September 2026 · this leaderboard is not ranked · Open the leaderboard