LLM Reference

Composer 2

Released
2026-03-19
Last refreshed
2026-06-29
Status
Researched 45d ago
ProprietaryCommercial use: unknownCodingRAGAgentsLong contextJSON / Tool use

Composer 2 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 200k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
Composer
Released
2026-03-19
Context
200k
Specialization
code
Openness
Proprietary
Weights
Not released
Code
Unknown
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 coding model released March 19, 2026. Fine-tuned from Moonshot AI's Kimi K2.5 checkpoint via continued pretraining and large-scale RL on long-horizon coding tasks. Scores 61.3 on CursorBench, 61.7 on Terminal-Bench 2.0 (vs. Claude Opus 4.6's 58.0), and 73.7 on SWE-bench Multilingual. Technical report: arxiv.org/abs/2603.24477. Available on all Cursor plans. Standard: $0.50/M input, $2.50/M output; Fast: $1.50/M input, $7.50/M output.

Composer 2 is a proprietary model in the Composer family. The structured metadata tracks a 200k-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 SWE-rebench 58.0, Terminal-Bench 2.0 61.7, and CursorBench 52.2.

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

Capabilities

Function CallingTool UseCode Execution

Benchmark peer barsfor Coding

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

Benchmark scores(3)

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
SWE-rebench58.0pass@1 (best of 5 runs)https://swe-rebench.com/leaderboard
Terminal-Bench 2.061.7Official Harbor evaluation framework (score)https://cursor.com/blog/composer-2
CursorBench52.2CursorBench 3.1https://cursor.com/evals

Migration checks

No linked migration route is available for this model yet.

Compare Composer 2 with other models

Frequently asked questions

What is the context window of Composer 2?

Composer 2 has a context window of 200k tokens.

How much does Composer 2 cost?

Composer 2 is available at $0.5/1M input tokens through Cursor.

When was Composer 2 released?

Composer 2 was released on 2026-03-19.

Which providers offer Composer 2?

Composer 2 is available from 1 provider: Cursor.

What benchmarks has Composer 2 been tested on?

Composer 2 has been evaluated on 3 benchmarks, including SWE-rebench, Terminal-Bench 2.0, CursorBench.