Cursor releases Composer 2.5, saying it's better at sustained work on long-running tasks and follows complex instructions more reliably; it's built on Kimi K2.5
Composer 2.5 is now available in Cursor. — It's a substantial improvement in intelligence and behavior over Composer 2.
Cursor
Related Coverage
- Cursor's Composer 2.5 matches Opus 4.7 and GPT-5.5 benchmarks at a fraction of the cost The Decoder · Matthias Bastian
- Cursor Introduces Composer 2.5 Hacker News
- Cursor Says Composer 2.5 Handles Longer Coding Jobs WinBuzzer · Markus Kasanmascheff
- Cursor released Composer 2.5 with up to 10x cost efficiency TestingCatalog AI News
Discussion
-
@cursor_ai
@cursor_ai
on x
Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we're doubling the included usage of the model. [image]
-
@elonmusk
Elon Musk
on x
Try it out! (Partially trained on Colossus 2)
-
@mntruell
Michael Truell
on x
Composer 2.5 is a significant step up from Composer 2. This is the very start of our work with SpaceXAI. Hope to have more improvements out soon.
-
@sjwhitmore
Sam Whitmore
on x
composer 2.5 is really really great. I had it on last week for some testing, forgot that it was on, & totally didn't realize I wasn't on gpt 5.5 (my usual) for a while. the team did a fantastic job!!
-
@cursor_ai
@cursor_ai
on x
Together with SpaceXAI, we're training a significantly larger model from scratch, using 10x more total compute. With Colossus 2's million H100-equivalents and our combined data and training techniques, we expect this to be a major leap in model capability.
-
@cursor_ai
@cursor_ai
on x
We improved Composer by scaling training, generating more complex RL environments, and introducing new learning methods. For example, we use text feedback during RL to learn faster by assigning credit in rollouts spanning hundreds of thousands of tokens.
-
@cursor_ai
@cursor_ai
on x
Composer 2.5 is built on the same open-source base as Composer 2, Moonshot's Kimi K2.5. [image]
-
@cursor_ai
@cursor_ai
on x
Composer 2.5 is exceptionally intelligent and up to 10x more efficient than similarly capable models. [image]
-
@mil000
Milo Smith
on x
Introducing [rebranded Chinese model] Its more intelligent (no shit) We are doubling usage forever. Hell, next week we might even triple it.
-
@eliebakouch
Elie
on x
cursor is at frontier scale, both in terms of performance and compute if composer 2.5's budget was put into a pre-train: ~6.3T total, 200B active trained on ~56T tokens if composer 3 allocates 50% of the budget to pre-training: ~500B active, 15.3T total trained on 135T tokens. [i…
-
@scaling01
@scaling01
on x
yeah that's pretty good xAI might be able to cook with Cursor data + 10T model [image]
-
@clementdelangue
Clem
on x
Very cool to see Cursor doubling down on training great models. In my opinion, ultimately all serious companies in AI will want to train models themselves, based on open-source instead of outsourcing AI to others via APIs!