Models · Cursor
Composer 2.5
Only from the makerNot on OpenRouterAvailable nowGenerally availableClosed (can't be downloaded)Proprietary
Composer 2.5 is made by Cursor. We don't have enough test results yet to rank it.
Cursor in-house coding model, only usable inside Cursor; not on OpenRouter.
- —
- —
- —
- Price unknown— / —
- —
- —
- —
- 2 (2 independent2 indep.)
- —
- Cursor
- —
Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.
You can't choose how long this one thinks.
No adjustable reasoning setting listed.
—
Every test result
Every result
All the numbers,with where they came from.
Every result we've found for this model, with who measured it and a link to where we read it.
All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.
| NotesNotes | ||||||
|---|---|---|---|---|---|---|
| CursorBench | 27.7% | DefaultComposer 2.5 | Independent testIndependentCursor (CursorBench) ↗ | 1 Oct 2026 | Cursor agent | CursorBench 4.0 (tasks from real Cursor sessions; v4.0 introduced 2026-09-10); rank 55; $0.68/task; 17,347 tokens/task; 41 steps/task |
| SWE-bench Verified | 79.6% | Default | Independent testIndependentVals.ai ↗ | 1 Sep 2026 | Cursor CLI | ±1.804 stderr; Vals archived SWE-bench Verified on 2026-09-01 (saturated) |