# Composer 2 Benchmark Scores & Performance

> Composer 2 by Cursor has 5 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/composer-2

Last updated: September 21, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Cursor |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 200K |
| Overall Score | Coming soon |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Composer
- Variant: base
- Benchmarks covered: 5 of 447
- Sibling models: [Composer 2.5](/models/composer-2-5), [Composer 2 Fast](/models/composer-2-fast)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Terminal-Bench 2.0](/benchmarks/terminal-bench-2) | 61.7% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 73.7% |
| [SWE-Rebench](/benchmarks/swe-rebench) | 58% |
| [React Native Evals](/benchmarks/reactnativeevals) | 96.1% |
| [Terminal-Bench 2.0](/benchmarks/terminal-bench-2) | 61.7% |

## Other Cursor Models

- [Composer 2.5](/models/composer-2-5) - Score: not computed
- [Composer 2 Fast](/models/composer-2-fast) - Score: not computed