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.
Not enough families covered yet.Add more benchmark rows for Composer 2.5 Fast to see the family profile.
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
Per-benchmark positions
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
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where Composer 2.5 Fast shows up, it's highlighted.