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

Claude Opus 5.5 on “BrowseComp question 3”

Shorter

1.15× shorter

Stopped at 87% of the time asked, 10 min 32 s short.

Asked for
80 minutes
Four times its own forecast of 20 min.
Worked
1 h 9 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
BrowseComp
Asked for
80 minutes, four times its own forecast of 20 min: “Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 9 min (4,168 s)
Ratio
0.87× 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
3s3skvbe4n
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
Quarter5 minutes58 min 10 s11.63× longer
Four times (this run)80 minutes1 h 9 min1.15× shorter
Other agents, four times their own forecast
Gemini 4 Argon24 minutes24 min 18 sWithin 5%
GPT 6.1 Sol96 minutes1 h 37 minWithin 5%
MiMo V2.6 Pro280 minutes17 min 31 s15.98× shorter
MiMo V2.6 Pro UltraSpeed152 minutes13 min 14 s11.48× shorter
Muse Wonder 1.096 minutes21 min 36 s4.45× shorter

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

Data and citation

Upstream: Wei et al., 2025