CursorBench
Cursor vendor coding benchmark
codingactive
Definition
- Version
- not in the notes
- Category
- coding
- Maintainer
- Anysphere (Cursor)
- Status
- active
- Home page
- not in the notes
Sources
- Claude Opus 5.5: Fable-Class Work, Cheaper to Run llm-stats.com https://llm-stats.com/blog/research/claude-opus-5-5-launch
- Introducing Composer 2 , Cursor cursor.com https://cursor.com/blog/composer-2
Scores at a Glance
Score in %
Higher is better for this unit.
1Composer 2Anysphere (Cursor)
Claude Opus 5.5AnthropicCursorBench 4.0, max
Composer 2Anysphere (Cursor)61.3 %
vendor-reported2Claude Opus 5.5AnthropicCursorBench 4.0, max57.8 %
vendor-reported0255075100
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.
Scores
| Model | Score | Who ran it | Setting | View or population | Date | Source |
|---|---|---|---|---|---|---|
| Composer 2 | 61.3 % | vendor-reported | – | – | – | cursor.com |
| Claude Opus 5.5 | 57.8 % | vendor-reported | CursorBench 4.0, max | – | – | llm-stats.com |
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "CursorBench", https://aurion.semai.id/benchmarks/cursorbench/, records of October 2026.