CursorBench

Measures: A coding agent must complete short, ambiguous, multi-file requests drawn from real Cursor sessions (editing, refactoring, investigation, intent understanding, managing jobs, design adherence); scored as a correctness percentage by agentic graders.

Maintainer: Cursor (Anysphere)
Introduced: 2026
Status: Active
Saturation: Headroom
Typical provenance: Independent
In scoring set: Yes

Official leaderboard

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.