Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-07-27 · high
The agent edits files and the DOM directly, falling back to a screen-reading helper on just 28 of 108 test tasks.
Why now: As of July 27, 2026, these numbers come only from OSWorld 2.0's current task set, with no independent replication yet.
Salesforce AI Research's new computer-use agent hits 26.9% success on OSWorld 2.0, roughly 9x cheaper per task than the same model reading screenshots, per a paper posted to arXiv.
Computer-use agents get billed and benchmarked on cost per completed task, and vision-based inference (reading a full screenshot after every click) is the expensive part. A 9x cost cut, with partial success up from 54.8% to 61.6%, changes that math for anyone running these agents at scale.
The agent, called StateAct, does most of its work by reading and editing files, backends, and the DOM directly through code instead of screenshots. It calls in a screenshot-reading GUI subagent only when code access isn't available.
That fallback fired on just 28 of 108 test tasks, covering 1.1% of the agent's steps.
The 20.6% figure it beat belongs to a screenshot-only version of the same Opus 4.8 model StateAct runs on.
Yes, but a code-only variant with no GUI subagent reached just 45.9% partial success, below the screenshot baseline, so the fallback earns its keep.
Each link below shares sources, entities, or timing with this story.
Claude Code uses Opus / Shared entity: Opus / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (code, cost).
Claude Code uses Opus / Shared entity: Opus / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (code, cost, subagent).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (agent, code, cost).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (agent, code, subagent).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (agent, code, cost).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (code, cost, task).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (agent, code, cost).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (agent, beat, cost).