ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast

MiMo V2.6 Pro on “luajit/luajit”

Shorter

3.83× shorter

Stopped at 26% of the time asked, 9 h 14 min short.

Asked for
12.5 hours
A quarter of its own forecast of 50 h.
Worked
3 h 16 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
12.5 hours, a quarter of its own forecast of 50 h: “Please work on this task for a full 12.5 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
3 h 16 min (11,741 s)
Ratio
0.26× 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
v7o52l6jk6
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
Quarter (this run)12.5 hours3 h 16 min3.83× shorter
Four times200 hours2 h 36 min76.74× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.51.08 hours52 min 10 s1.24× shorter
Gemini 4 Argon23.75 minutes46 min 19 s1.95× longer
GPT 6.1 Sol37.5 minutes37 min 50 sWithin 5%
MiMo V2.6 Pro UltraSpeed17.5 hours2 h 42 min6.47× shorter
Muse Wonder 1.010 hours14 min 10 s42.37× shorter

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

Data and citation

Upstream: Yang et al., 2026