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

MiMo V2.6 Pro on “BrowseComp question 2”

Shorter

36.75× shorter

Stopped at 3% of the time asked, 2 h 20 min short.

Asked for
144 minutes
Four times its own forecast of 36 min.
Worked
3 min 55 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
MiMo V2.6 Pro, in MiMo Code
Benchmark
BrowseComp
Asked for
144 minutes, four times its own forecast of 36 min: “Please work on this task for a full 144 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
3 min 55 s (235 s)
Ratio
0.03× 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
qrl2r53n7q
Data release
2 Nov 2026
The other ask for MiMo V2.6 Pro on this task, and the other agents at the same share of their own time
MiMo Pro on this taskAskedWorkedSplitResult
Quarter9 minutes8 min 26 s1.07× shorter
Four times (this run)144 minutes3 min 55 s36.75× shorter
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%
GPT 6.1 Sol20 minutes20 min 51 sWithin 5%
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