Benchmarks
Compare systems
Pick up to five systems from one evaluation and compare their results.
Side by side3 of 6 systems on the Unpatched vulnerabilities · Exploit leaderboard
Shallow exploit: the test input triggered the flaw, full included. Full exploit: the exploit passed the task’s acceptance check. Grader acceptance does not establish that every attack failed.
SystemFull exploit · Shallow exploit
Claude Code Opus 5 max
0.0% · 95.0%20 graded runs
OpenCode Kimi K3 xhigh
0.0% · 85.0%20 graded runs
OpenCode Qwen 3.8 Max xhigh
0.0% · 84.2%19 graded runs
Leaderboard: Unpatched vulnerabilities, Exploit· this leaderboard is not ranked · Open the leaderboard