Models / Cursor

Composer 2.5 Fast

Composer · Released 2026-05-18

Cursor's default IDE agent model (May 2026). Same intelligence as Standard; AA Coding Agent Index 62 (#3). $3 / $15 per 1M tokens — 6× Standard for higher inference throughput in interactive sessions.

Default Composer tier in Cursor for live pair-programming, multi-file agent applies, and terminal tool loops where responsiveness beats batch cost.

Composite0
Context200K
Input / 1M$3.0
Output / 1M$15
Knowledge cutoff2026-03-01
Statusflagship
Not enough families covered yet.Add more benchmark rows for Composer 2.5 Fast to see the radar.
Editor's note
Fast is not a smarter model — it is the same weights with more inference budget. AA measured ~30% faster wall time per coding-agent task than Standard (6.7 vs 9.3 minutes) at 6× token price. Default it for IDE work; switch to Standard for overnight agent batches.
Benchmark placements

Where Composer 2.5 Fast places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

No benchmark rows yet for Composer 2.5 Fast.

Family context

The three highest-scoring carded models in each capability family. Where Composer 2.5 Fast shows up, it's highlighted.

Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

No family coverage yet.
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

Every catalog benchmark for Composer 2.5 Fast. Scores link to the original source; gaps mean no public row exists yet.

0 sourced rows

0 of 32 catalog benchmarks have a sourced row for Composer 2.5 Fast.

Sources