Composer 2.5
Composer 2.5 is a coding model from Cursor, released on 2026-05-18. It accepts text input and returns text output. The recorded context window is 200K. Cataloged capabilities include Coding model. The model weights are proprietary and are not published for download. Use the linked references to confirm current access, licensing, and provider-specific limits.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $0.500/ 1M | $2.50/ 1M |
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $3.00/ 1M | $15.00/ 1M |
Composer 2.5 currently shows benchmark results led by SWE-bench Multilingual (3 / 23, score 79.80), Terminal Bench 2.0 (7 / 47, score 69.30). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
No curated comparisons for this model yet.
Want a custom combination? Open the compare tool
Composer 2.5 is a coding model from Cursor, released on 2026-05-18.
It accepts text input and produces text output. Its cataloged capabilities include Coding model. The recorded context window is 200K.
The model weights are proprietary and are not published for download. The page records 4 API pricing rules from Cursor; current provider pricing and conditions should be checked before deployment. The evaluation section contains 2 cataloged benchmark results with their recorded modes and scores. The page links 1 release, model-card, repository, or provider references for checking the underlying claims. Specifications, availability, and prices can change; undisclosed values are intentionally left unstated.
Composer 2.5 is a coding model from Cursor, released on 2026-05-18. It accepts text input and returns text output. The recorded context window is 200K. Cataloged capabilities include Coding model. The model weights are proprietary and are not published for download. Use the linked references to confirm current access, licensing, and provider-specific limits.
The current model record lists text as input and text as output.
The recorded context window is 200K. Fields without a source-backed value remain undisclosed.
The page records 4 API pricing rules from Cursor; current provider pricing and conditions should be checked before deployment.
The evaluation section contains 2 cataloged benchmark results with their recorded modes and scores. Compare only results that use the same benchmark version and evaluation mode.
The model weights are proprietary and are not published for download. Review the linked license text before commercial or derivative use.
Follow DataLearner on WeChat for AI model updates and research notes.
