Microsoft releases 4B hybrid computer-use agent scoring 66% on OSWorld
_akhaliq · x · 2026-10-31
Microsoft released a 4B hybrid computer-use agent on Hugging Face — a single compact policy that decides when to click and when to code. It scores 66.0% on OSWorld-Verified, beating 27B/30B agents and nearing the human 72.4% baseline (frontier GPT-5.5 sits at 78.7). A notable result for locally deployable computer-use agents.
More from Models
- ThursdAI crew debates: with Opus 7 coming, who still cares about better benchmarks? — thursdai_pod · 2026-10-31
- 14 models tested on 960 analyst tasks: AI scores 97/100 as analyst, picks winners no better than random — HeyAmit_ · 2026-10-31
- Anthropic adds invisible text watermark to Claude outputs starting Nov 3 — petesena · 2026-10-31
- GPT-6 Luna vs GPT-6.1 Terra vs GPT-6.1 Sol vs GPT-6 Astra in Pixel Art — Angaisb_ · 2026-10-31
- Perplexity engineer invites public tasks to prove or fix pplx-decider's SOTA claims — antoine_chaffin · 2026-10-31
- Arena weekly: Gemini 4 Carbon tops Text Arena, GPT-6.1 Terra enters Agent Arena at #8 — arena · 2026-10-31