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

GPT 6.1 Sol on “Shotcut montage project”

Shorter

4.38× shorter

Stopped at 23% of the time asked, 2 h 19 min short.

Asked for
180 minutes
Four times its own forecast of 45 min.
Worked
41 min 8 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
180 minutes, four times its own forecast of 45 min: “Please work on this task for a full 180 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
41 min 8 s (2,468 s)
Ratio
0.23× 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
ocmcbmg5ii
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
Quarter11.25 minutes12 min 34 s1.12× longer
Four times (this run)180 minutes41 min 8 s4.38× shorter
Other agents, four times their own forecast
Claude Opus 5.5380 minutes53 min 42 s7.08× shorter
Gemini 4 Argon88 minutes2 h 28 min1.68× longer
MiMo V2.6 Pro480 minutes4 h 41 min1.71× shorter
MiMo V2.6 Pro UltraSpeed320 minutes2 h 45 min1.94× shorter

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

Data and citation

Upstream: Yuan et al., 2026