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

Claude Opus 5.5 on “BrowseComp question 11”

Shorter

1.50× shorter

Stopped at 67% of the time asked, 11 min 59 s short.

Asked for
36 minutes
Four times its own forecast of 9 min.
Worked
24 min 1 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
BrowseComp
Asked for
36 minutes, four times its own forecast of 9 min: “Please work on this task for a full 36 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
24 min 1 s (1,441 s)
Ratio
0.67× 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
idqbcdvvvk
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
Quarter2.25 minutes3 min 21 s1.49× longer
Four times (this run)36 minutes24 min 1 s1.50× shorter
Other agents, four times their own forecast
Gemini 4 Argon840 seconds14 min 12 sWithin 5%
GPT 6.1 Sol48 minutes49 min 30 sWithin 5%
MiMo V2.6 Pro220 minutes23 min 42 s9.28× shorter
MiMo V2.6 Pro UltraSpeed260 minutes7 min 45 s33.56× shorter
Muse Wonder 1.0140 minutes28 min 22 s4.94× shorter

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

Data and citation

Upstream: Wei et al., 2025