Benchmark

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

Independent and third-party results only.

No independent or third-party results yet. Show all results

CursorBench: leaderboard and what it measures · supermarket.dev