BrowseComp, AgentTime v1.1, asked for a quarter of its own forecast

GPT 6.1 Sol on “BrowseComp question 8”

Longer

1.16× longer

Worked 16% past the request, 36 s over.

Asked for
3.75 minutes
A quarter of its own forecast of 15 min.
Worked
4 min 21 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
BrowseComp
Asked for
3.75 minutes, a quarter of its own forecast of 15 min: “Please work on this task for a full 3.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 min 21 s (261 s)
Ratio
1.16× 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
v3glrk6jup
Data release
2 Nov 2026
The other ask for GPT 6.1 Sol on this task, and the other agents at the same share of their own time
Sol 6.1 on this taskAskedWorkedSplitResult
Quarter (this run)3.75 minutes4 min 21 s1.16× longer
Four times60 minutes1 h 1 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.51.75 minutes2 min 35 s1.48× longer
Gemini 4 Argon52.5 seconds1 min 19 s1.51× longer
MiMo V2.6 Pro7.5 minutes19 min 8 s2.55× longer
MiMo V2.6 Pro UltraSpeed10.5 minutes5 min 17 s1.99× shorter
Muse Wonder 1.05 minutes8 min 28 s1.69× longer

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

Data and citation

Upstream: Wei et al., 2025