OSWorld 2.0, AgentTime v1.1, asked for a quarter of its own forecast

GPT 6.1 Sol on “Twenty recurring meetings”

Within 5%

Within 5%

Worked 101% of the time asked, within 5% of it.

Asked for
22.5 minutes
A quarter of its own forecast of 1 h 30 min.
Worked
22 min 46 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
OSWorld 2.0
Asked for
22.5 minutes, a quarter of its own forecast of 1 h 30 min: “Please work on this task for a full 22.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
22 min 46 s (1,366 s)
Ratio
1.01× the request
How it ended
Ended on its own
Grade
Not graded
Clock tool
The agent could call a wall-clock tool to read the current time.
Wording
The paper's standard sentence, sent in AgentTime v1.1.
Run id
bztjebym7w
Data release
2 Nov 2026
The other ask for GPT 6.1 Sol on this task, and the other agents at the same share of their own time
Sol 6.1 on this taskAskedWorkedSplitResult
Quarter (this run)22.5 minutes22 min 46 sWithin 5%
Four times360 minutes15 min 22 s23.44× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.535 minutes46 min 46 s1.34× longer
Gemini 4 Argon7 minutes28 min 42 s4.10× longer
MiMo V2.6 Pro17.5 minutes4 h 11 min14.33× longer
MiMo V2.6 Pro UltraSpeed18 minutes19 min 56 s1.11× longer
Muse Wonder 1.030 minutes19 min 29 s1.54× shorter

See it on the chart. Transcripts are not published yet.

Data and citation

Upstream: Yuan et al., 2026