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

MiMo V2.6 Pro on “BrowseComp question 9”

Shorter

5.15× shorter

Stopped at 19% of the time asked, 1 h 21 min short.

Asked for
100 minutes
Four times its own forecast of 25 min.
Worked
19 min 24 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
100 minutes, four times its own forecast of 25 min: “Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
19 min 24 s (1,164 s)
Ratio
0.19× 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
hci2wpgdp5
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
Quarter6.25 minutes47 min 59 s7.68× longer
Four times (this run)100 minutes19 min 24 s5.15× shorter
Other agents, four times their own forecast
Claude Opus 5.548 minutes49 min 31 sWithin 5%
Gemini 4 Argon720 seconds13 min 15 s1.10× longer
GPT 6.1 Sol48 minutes48 min 59 sWithin 5%
MiMo V2.6 Pro UltraSpeed140 minutes3 min 28 s40.48× shorter
Muse Wonder 1.072 minutes1 h 12 minWithin 5%

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

Data and citation

Upstream: Wei et al., 2025