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

GPT 6.1 Sol on “BrowseComp question 2”

Within 5%

Within 5%

Worked 104% of the time asked, within 5% of it.

Asked for
20 minutes
Four times its own forecast of 5 min.
Worked
20 min 51 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
20 minutes, four times its own forecast of 5 min: “Please work on this task for a full 20 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
20 min 51 s (1,251 s)
Ratio
1.04× 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
7wg3qpwp2e
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
Quarter1.25 minutes1 min 48 s1.44× longer
Four times (this run)20 minutes20 min 51 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.532 minutes35 min 26 s1.11× longer
Gemini 4 Argon720 seconds12 min 20 sWithin 5%
MiMo V2.6 Pro144 minutes3 min 55 s36.75× shorter
MiMo V2.6 Pro UltraSpeed220 minutes5 min 14 s42.01× shorter
Muse Wonder 1.0120 minutes7 min 8 s16.83× shorter

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

Data and citation

Upstream: Wei et al., 2025