Composer 2.5
Cursor’s most powerful model yet
Composer 2.5 launched on May 19, 2026 with 431 votes, #29 of 20,539 launches that month and more than 99% of that year's launches.
In plain words
Composer 2.5 is an AI model designed for development tasks, offering improvements over its predecessor in intelligence and capability. It is built for developers and teams working on complex, long-horizon agentic tasks that require sustained reasoning and planning. The model stands out for its enhanced performance on extended projects where AI needs to work autonomously across multiple steps toward a goal.
written from the facts on this page · September 2026
From the sources
A substantial improvement in intelligence and behavior over Composer 2, particularly on long-horizon agentic tasks.
It's a substantial improvement in intelligence and behavior over Composer 2 . It is better at sustained work on long-running tasks, follows complex instructions more reliably, and is more pleasant to collaborate with. We improved Composer by scaling training, generating more complex RL environments, and introducing new learning methods. In addition to training Composer 2.5 on more difficult tasks, we improved behavioral aspects of the model like communication style and effort calibration. These dimensions are not well captured by existing benchmarks, but we find that they matter for real-world usefulness. Composer 2.5 is built on the same open-source checkpoint as Composer 2, Moonshot's…from cursor.com
Does a similar job
all alternatives →More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 19d ago · stillwet.art

PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai



Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com

🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com