OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast

GPT 6.1 Sol on “Defense schedule”

Within 5%

Within 5%

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

Asked for
100 minutes
Four times its own forecast of 25 min.
Worked
1 h 41 min
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
100 minutes, four times its own forecast of 25 min: “Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 41 min (6,050 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
k3lakiqiud
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
Quarter6.25 minutes6 min 23 sWithin 5%
Four times (this run)100 minutes1 h 41 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.5108 minutes43 min 35 s2.48× shorter
Gemini 4 Argon40 minutes45 min 36 s1.14× longer
MiMo V2.6 Pro56 minutes1 h 52 min2.00× longer
MiMo V2.6 Pro UltraSpeed140 minutes3 h1.28× longer

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

Data and citation

Upstream: Yuan et al., 2026