What is Composer 2.5?
Composer 2.5 is Cursor’s proprietary agentic coding model, designed for long-horizon tasks and positioned as a cost-efficient alternative to frontier models like Opus 4.7 and GPT-5.5. It is positioned as a cost-efficient alternative to leading models like Opus 4.7 and GPT-5.5, with comparable performance at significantly lower cost.
Release history
- May 2026 - Nathaniel Whittemore reported that Composer 2.5 scored 69.3% on Terminal Bench 2.0, just behind Opus 4.7.
- May 2026 - On SweBench multilingual, Composer 2.5 scored comparable to Opus 4.7 (80.5%) and GPT-5.5 (77.8%), per Whittemore.
- May 2026 - Whittemore noted that Composer 2.5 performed comparably to Opus 4.7 and GPT-5.5, slightly ahead on medium settings and slightly behind on extra high and max settings, but at 10 to 60x lower cost.
- May 2026 - According to Whittemore, Cursor claims their model is 10x more efficient compared to similarly capable models.
In the discourse
Attributed discussion of Composer 2.5.
Cursor's Composer 2.5 scores 69.3% on Terminal Bench 2.0 and is comparable to Opus 4.7 (80.5%) and GPT-5.5 (77.8%) on SweBench multilingual.
“It scored 69.3% on Terminal Bench 2.0, which is just behind Opus 4.7 On SweBench multilingual, it scored comparable to both Opus 4.7 at 80.5% and GPT-5.5 at 77.8%.”Nathaniel Whittemore · 20 May 2026
Cursor Composer 2.5 matched or approached Opus 4.7 and GPT 5.5 performance at 10 to 60x lower cost, making it a significant efficiency play for enterprise coding workloads.
“It performed at a very comparable level to Opus 4.7 and GPT 5.5, a little ahead of them on their medium settings and a little below them on extra high and max settings, but it did all that at 10 to 60x lower cost.”Nathaniel Whittemore · 24 May 2026
Cursor Composer 2.5 achieved comparable performance to Opus 4.7 and GPT 5.5 at 10 to 60x lower cost.
“It performed at a very comparable level to Opus 4.7 and GPT 5.5, a little ahead of them on their medium settings and a little below them on extra high and max settings, but it did all that at 10 to 60x lower cost.”Nathaniel Whittemore · 24 May 2026
Cursor's Composer 2.5 claims 10x efficiency over similarly capable models, a potential structural cost advantage in the AI coding market.
“That has led Cursor to claim that their model is 10x more efficient compared to similarly capable models.”Nathaniel Whittemore · 20 May 2026