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

Claude Opus 5.5 on “Zotero, Obsidian, and BibTeX”

Shorter

3.12× shorter

Stopped at 32% of the time asked, 2 h 43 min short.

Asked for
240 minutes
Four times its own forecast of 1 h.
Worked
1 h 17 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
240 minutes, four times its own forecast of 1 h: “Please work on this task for a full 240 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 17 min (4,622 s)
Ratio
0.32× 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
6yzsvhau6a
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
Quarter15 minutes38 min 26 s2.56× longer
Four times (this run)240 minutes1 h 17 min3.12× shorter
Other agents, four times their own forecast
Gemini 4 Argon100 minutes40 s149.25× shorter
GPT 6.1 Sol260 minutes1 h 7 min3.88× shorter
MiMo V2.6 Pro380 minutes3 h 58 min1.60× shorter
MiMo V2.6 Pro UltraSpeed340 minutes4 h 2 min1.41× shorter

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

Data and citation

Upstream: Yuan et al., 2026