LLM Reference

Composer 2.5

Released
2026-05-18
Last refreshed
2026-06-30
Status
Researched 3d ago
ProprietaryCommercial use: conditionalCodingRAGAgentsLong contextJSON / Tool use

Composer 2.5 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 1m context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
Composer
Released
2026-05-18
Context
1m
Specialization
code
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Not released
Created by

AI-driven multi-file code generation

Buffalo, New York, United States
Founded 2022
Website
Pricing
Output / 1M
$2.50
Input / 1M
$0.500

Cheapest of 1 route · Cursor

About

Cursor's agentic coding model released May 18, 2026. Built on Moonshot AI's Kimi K2.5 open-source checkpoint with targeted RL using textual feedback and 25× more synthetic training tasks than Composer 2. Designed for long-horizon software engineering tasks: multi-file edits, terminal command execution, codebase-wide semantic search, and autonomous task planning. Uses Cursor's compaction-in-the-loop context management for long coding sessions. Available on all Cursor plans; accessed through the Cursor IDE (not a standalone API). Standard pricing: $0.50/M input, $2.50/M output; Fast (default): $3.00/M input, $15.00/M output.

Composer 2.5 is a proprietary model in the Composer family. The structured metadata tracks a 1m-token context window, function calling, tool use, and code execution. This page tracks provider routes through Cursor, with the cheapest tracked route listed at $0.5 input and $2.5 output per 1M tokens. Headline tracked benchmarks include Terminal-Bench 2.0 69.3, SWE-bench Multilingual 79.8, and CursorBench 63.2.

Top use-case fit: coding, agents, and build tasks

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Cursor$0.500$2.50
Serverless

Capabilities

Function CallingTool UseCode Execution

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Terminal-Bench 2.069.3Terminal-Bench 2.0https://www.buildfastwithai.com/blogs/cursor-composer-2-5-review-2026
SWE-bench Multilingual79.8SWE-bench Multilingualhttps://getaibook.com/news/cursor-composer-25-hits-798-on-swe-bench-multilingual/; https://www.buildfastwithai.com/blogs/cursor-composer-2-5-review-2026
CursorBench63.2CursorBench 3.1https://cursor.com/evals
SWE-rebench79.8Reported as SWE-bench Multilingual (300 tasks, 9 languages) (resolved%)https://cursor.com/blog/composer-2-5

Migration checks

No linked migration route is available for this model yet.

Compare Composer 2.5 with other models

Show all 15 popular comparisonssorted by 7-day search impressions

Frequently asked questions

What is the context window of Composer 2.5?

Composer 2.5 has a context window of 1m tokens.

How much does Composer 2.5 cost?

Composer 2.5 is available at $0.50/1M input tokens through Cursor.

When was Composer 2.5 released?

Composer 2.5 was released on 2026-05-18.

Which providers offer Composer 2.5?

Composer 2.5 is available from 1 provider: Cursor.

What benchmarks has Composer 2.5 been tested on?

Composer 2.5 has been evaluated on 4 benchmarks, including Terminal-Bench 2.0, SWE-bench Multilingual, CursorBench, SWE-rebench.