Composer 2 Benchmark Scores & Performance

BenchLM is tracking Composer 2 by Cursor. Some benchmark data is visible, but not enough non-generated coverage is available for a leaderboard rank yet.

BenchLM is tracking Composer 2, but this profile is currently excluded from the public leaderboard because it still lacks enough trustworthy benchmark coverage to rank safely. Generated rows may still appear below for context, but they are not enough on their own to make this model ranking-eligible.

Composer 2 is a proprietary model with a 200K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

This profile currently has 3 of 61 tracked benchmarks. BenchLM uses discounted fallback estimates where necessary so missing categories do not collapse the overall score, but public sourced rows still carry more weight than inferred ones.

Creator

Cursor

Source Type

Proprietary

Reasoning

Reasoning

Context Window

200K

Release Date

Mar 19, 2026

Overall Score

Unranked

Rankings Overview

BenchLM is still missing enough trustworthy benchmark coverage to rank this model across the public leaderboard. Trusted benchmark rows remain visible below for reference.

Coding Benchmarks

SWE Multilingual
73.7%
React Native Evals
97.2%

Agentic Benchmarks

Terminal-Bench 2.0
61.7%

Frequently Asked Questions

How does Composer 2 perform overall in AI benchmarks?

Composer 2 has 3 sourced benchmark scores on BenchLM, but it does not yet have enough trustworthy non-generated coverage to receive a global overall rank.

Is Composer 2 good for coding and programming?

Composer 2 has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.

Is Composer 2 good for agentic tool use and computer tasks?

Composer 2 has visible benchmark coverage in agentic tool use and computer tasks, but BenchLM does not currently assign it a global category rank there.

Does Composer 2 have full benchmark coverage on BenchLM?

Not yet. Composer 2 currently has 3 sourced benchmark scores out of the 61 benchmarks BenchLM tracks. BenchLM may use discounted fallback values for missing categories, but trustworthy public rows still carry more weight than inferred ones.

What is the context window size of Composer 2?

Composer 2 has a context window of 200K, which determines how much text it can process in a single interaction.

Last updated: March 18, 2026

Weekly LLM Updates

New model releases, benchmark scores, and leaderboard changes. Every Friday.

Free. Your signup is stored with a derived country code for compliance routing.