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

MiMo V2.6 Pro UltraSpeed on “Reimbursement package”

Shorter

2.25× shorter

Stopped at 44% of the time asked, 48 min 56 s short.

Asked for
88 minutes
Four times its own forecast of 22 min.
Worked
39 min 4 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
MiMo V2.6 Pro UltraSpeed, in MiMo Code
Benchmark
OSWorld 2.0
Asked for
88 minutes, four times its own forecast of 22 min: “Please work on this task for a full 88 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
39 min 4 s (2,344 s)
Ratio
0.44× 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
k64fhbcxds
Data release
2 Nov 2026
The other ask for MiMo V2.6 Pro UltraSpeed on this task, and the other agents at the same share of their own time
MiMo UltraSpeed on this taskAskedWorkedSplitResult
Quarter5.5 minutes1 h 9 min12.56× longer
Four times (this run)88 minutes39 min 4 s2.25× shorter
Other agents, four times their own forecast
Claude Opus 5.5140 minutes31 min 32 s4.44× shorter
Gemini 4 Argon48 minutes48 min 50 sWithin 5%
GPT 6.1 Sol104 minutes1 h 45 minWithin 5%
MiMo V2.6 Pro80 minutes2 min 23 s33.47× shorter

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

Data and citation

Upstream: Yuan et al., 2026