CursorBench A
AI benchmark · Coding
What is CursorBench?
Cursor's agentic coding benchmark composed of real coding tasks (drawn from internal use and external traffic) executed in Cursor's production agent harness; scores and per-task costs are measured and reported independently by Cursor.
Tier A
Widely used: a lab reports it, or 50 or more models are scored on it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 3 models scored
- reported by Anthropic
- in curated RL directories (2 pts)
On X · well regarded, moderate buzz, from 9 posts about CursorBench in the last month
CursorBench 4.0 scores are cited in model launch tables and comparisons; some see it as closer to real coding feel, though it is Cursor's own benchmark.
How we got to tier A
- Adoption: 3 models scored; reported by Anthropic. Tier A.
- On X: well regarded, moderate buzz. “CursorBench 4.0 scores are cited in model launch tables and comparisons; some see it as closer to real coding feel, though it is Cursor's own benchmark.” No move.
- In curated RL directories: 2 points, a floor of C.
- Not yet confirmed by a line from its own site or paper.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Not on the map yet: no line from its own site or paper places it in a domain.
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.