Cursor · 2026-05-18 · major
Cursor Composer 2.5 — Coding Model Matches Opus 4.7 and GPT-5.5 on SWE-Bench Multilingual at a Fraction of the Cost
Cursor's updated in-house coding model scores 79.8% on SWE-Bench Multilingual and 63.2% on CursorBench v3.1, matching Opus 4.7 and GPT-5.5 while charging $0.50/$2.50 per million input/output tokens.
Cursor's in-house coding model now matches frontier models on coding benchmarks at a fraction of the price.
Key specs
| Price (input) | $0.50/M tokens |
|---|---|
| Price (output) | $2.50/M tokens |
| Swe bench multilingual | 79.8% |
| Cursor bench v3.1 | 63.2% |
What is it?
Composer 2.5 is the latest version of Cursor's own coding model, built into the Cursor editor. It is tuned for sustained work on long-running tasks and for following complex instructions, and replaces Composer 2 as Cursor's default agent model.
How does it work?
It is built on Moonshot's open-source Kimi K2.5 checkpoint, with 85% of the compute budget spent on additional training and reinforcement learning. Cursor trained it on 25x more synthetic tasks than Composer 2, including feature-deletion exercises grounded in real codebases, and used targeted textual feedback that inserts corrections at the exact point in a trajectory where the model went wrong.
Why does it matter?
On SWE-Bench Multilingual (79.8%) and CursorBench v3.1 (63.2%), Composer 2.5 matches Opus 4.7 and GPT-5.5 while charging $0.50/$2.50 per million input/output tokens — well below what Anthropic and OpenAI charge. Cursor says a typical task runs under a dollar versus up to eleven for rival models.
Who is it for?
developers using Cursor
Try it
Select Composer 2.5 in Cursor's model picker