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

MiMo V2.6 Pro on “BrowseComp question 10”

Shorter

2.01× shorter

Stopped at 50% of the time asked, 2 h 1 min short.

Asked for
240 minutes
Four times its own forecast of 1 h.
Worked
1 h 59 min
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
240 minutes, four times its own forecast of 1 h: “Please work on this task for a full 240 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 59 min (7,162 s)
Ratio
0.50× 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
xqdxbxi5qu
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
Quarter15 minutes36 min 52 s2.46× longer
Four times (this run)240 minutes1 h 59 min2.01× shorter
Other agents, four times their own forecast
Claude Opus 5.5120 minutes2 hWithin 5%
Gemini 4 Argon48 minutes48 min 19 sWithin 5%
GPT 6.1 Sol96 minutes1 h 37 minWithin 5%
MiMo V2.6 Pro UltraSpeed120 minutes15 min 32 s7.72× shorter
Muse Wonder 1.048 minutes49 min 40 sWithin 5%

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

Data and citation

Upstream: Wei et al., 2025