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

Claude Opus 5.5 on “Twenty recurring meetings”

Shorter

6.71× shorter

Stopped at 15% of the time asked, 7 h 57 min short.

Asked for
560 minutes
Four times its own forecast of 2 h 20 min.
Worked
1 h 23 min
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
560 minutes, four times its own forecast of 2 h 20 min: “Please work on this task for a full 560 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 23 min (5,004 s)
Ratio
0.15× 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
ikazfpvpgz
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
Quarter35 minutes46 min 46 s1.34× longer
Four times (this run)560 minutes1 h 23 min6.71× shorter
Other agents, four times their own forecast
Gemini 4 Argon112 minutes34 min 26 s3.25× shorter
GPT 6.1 Sol360 minutes15 min 22 s23.44× shorter
MiMo V2.6 Pro280 minutes4 h 55 min1.05× longer
MiMo V2.6 Pro UltraSpeed288 minutes5 h 25 min1.13× longer

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

Data and citation

Upstream: Yuan et al., 2026