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

MiMo V2.6 Pro on “tomarrell/wrapcheck”

Shorter

16.66× shorter

Stopped at 6% of the time asked, 22 h 34 min short.

Asked for
24 hours
Four times its own forecast of 6 h.
Worked
1 h 26 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
ProgramBench
Asked for
24 hours, four times its own forecast of 6 h: “Please work on this task for a full 24 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 26 min (5,187 s)
Ratio
0.06× 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
tlhle65zot
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
Quarter1.5 hours1 h 19 min1.14× shorter
Four times (this run)24 hours1 h 26 min16.66× shorter
Other agents, four times their own forecast
Claude Opus 5.5300 minutes2 h 20 min2.14× shorter
Gemini 4 Argon168 minutes3 min 24 s49.41× shorter
GPT 6.1 Sol240 minutes4 h 1 minWithin 5%
MiMo V2.6 Pro UltraSpeed28 hours53 min 27 s31.43× shorter
Muse Wonder 1.020 hours9 min 50 s122.08× shorter

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

Data and citation

Upstream: Yang et al., 2026