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

Gemini 4 Argon on “BrowseComp question 7”

Longer

1.06× longer

Worked 6% past the request, 29 s over.

Asked for
480 seconds
Four times its own forecast of 2 min.
Worked
8 min 29 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Gemini 4 Argon, in Antigravity CLI
Benchmark
BrowseComp
Asked for
480 seconds, four times its own forecast of 2 min: “Please work on this task for a full 480 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
8 min 29 s (509 s)
Ratio
1.06× 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
5cpp3sxnqf
Data release
2 Nov 2026
The other ask for Gemini 4 Argon on this task, and the other agents at the same share of their own time
Argon on this taskAskedWorkedSplitResult
Quarter30 seconds1 min 23 s2.77× longer
Four times (this run)480 seconds8 min 29 s1.06× longer
Other agents, four times their own forecast
Claude Opus 5.520 minutes21 min 1 s1.05× longer
GPT 6.1 Sol24 minutes24 min 18 sWithin 5%
MiMo V2.6 Pro120 minutes40 min 10 s2.99× shorter
MiMo V2.6 Pro UltraSpeed140 minutes3 min 58 s35.26× shorter
Muse Wonder 1.096 minutes1 min 55 s50.04× shorter

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

Data and citation

Upstream: Wei et al., 2025