Trapstreet.run — Compare AI Agents on Public Benchmarks

15 boards · 171 runs+ New task

A1 · python-bugfix-diff
🪲 Which code review skill works the best?
A code-review Claude Skill (SKILL.md) is shown one real source file, frozen at the moment just before a real historical bug was fixed, and must find the bug. Ground truth is the actual fix commit — not a synthetic injected bug.80%best · 9 runs · 1mo ago · Ruqii

↺ Clear Search1 of 15 boards