CursorBench 3.2 A
AI benchmark · Coding
What is CursorBench 3.2?
Version 3.2 of Cursor's agentic coding benchmark, evaluated in Cursor's production agent harness.
Tier A
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.
- 17 models scored
- reported by xAI
- in curated RL directories (1 pt)
On X · well regarded, moderate buzz, from 2 posts about CursorBench 3.2 in the last month
CursorBench 3.2 scores are cited as a standard coding metric in model comparisons and cost-per-task analyses, without complaints about its validity.
How we got to tier A
- Adoption: 17 models scored; reported by xAI. Tier A.
- On X: well regarded, moderate buzz. “CursorBench 3.2 scores are cited as a standard coding metric in model comparisons and cost-per-task analyses, without complaints about its validity.” No move.
- In curated RL directories: 1 point, a floor of none.
- 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.