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

Claude Opus 5.5 on “Reimbursement package”

Shorter

4.44× shorter

Stopped at 23% of the time asked, 1 h 48 min short.

Asked for
140 minutes
Four times its own forecast of 35 min.
Worked
31 min 32 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Claude Opus 5.5, in Claude Code
Benchmark
OSWorld 2.0
Asked for
140 minutes, four times its own forecast of 35 min: “Please work on this task for a full 140 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
31 min 32 s (1,892 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
32lojzxqcb
Data release
2 Nov 2026
The other ask for Claude Opus 5.5 on this task, and the other agents at the same share of their own time
Opus 5.5 on this taskAskedWorkedSplitResult
Quarter8.75 minutes10 min 11 s1.16× longer
Four times (this run)140 minutes31 min 32 s4.44× shorter
Other agents, four times their own forecast
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
MiMo V2.6 Pro UltraSpeed88 minutes39 min 4 s2.25× shorter

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

Data and citation

Upstream: Yuan et al., 2026