Simular Agent S4: open 27B model beats GPT-5.5 at computer use
Why it matters
Simular's Agent S4 doesn't solve tasks itself: it studies computer-use agents and improves the interfaces they work through. A meta-agent reads the task agents' trajectories and rewrites a repository of interfaces, and population-based evolution decides which versions get developed further. It learns only from synthetic training tasks; the meta-agent never sees a benchmark task. With the evolved interfaces, the open Qwen3.8-27B model reaches 21.3% binary success on the full 108-task OSWorld V2 benchmark, 3.8 times the same model with fixed interfaces, above GPT-5.5 (13.0%) and just above Claude Opus 4.8 (20.6%), at about $1.10 per task versus $25.50 and $72.40. On ScienceBoard, the success rate rises from 41.4% to 58.6% with the same model. Caveats: OSWorld V2 is scored as strict pass/fail, so most tasks still fail, and these are Simular's own published results. The code is open source.
Read the source: Simular (blog) (opens in a new tab)
All hits from 24 Oct 2026More AgentsGet the daily hits by email