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

Claude Opus 5.5 on “MuseScore transcription”

Longer

1.13× longer

Worked 13% past the request, 42 min 49 s over.

Asked for
320 minutes
Four times its own forecast of 1 h 20 min.
Worked
6 h 3 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
320 minutes, four times its own forecast of 1 h 20 min: “Please work on this task for a full 320 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
6 h 3 min (21,769 s)
Ratio
1.13× 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
kjexpbsfam
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
Quarter20 minutes31 min 22 s1.57× longer
Four times (this run)320 minutes6 h 3 min1.13× longer
Other agents, four times their own forecast
Gemini 4 Argon80 minutes43 min 11 s1.85× shorter
GPT 6.1 Sol360 minutes4 h 14 min1.42× shorter
MiMo V2.6 Pro600 minutes6 h 6 min1.64× shorter
MiMo V2.6 Pro UltraSpeed360 minutes4 h 16 min1.41× shorter

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

Data and citation

Upstream: Yuan et al., 2026