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

MiMo V2.6 Pro UltraSpeed on “luajit/luajit”

Shorter

6.47× shorter

Stopped at 15% of the time asked, 14 h 48 min short.

Asked for
17.5 hours
A quarter of its own forecast of 70 h.
Worked
2 h 42 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
MiMo V2.6 Pro UltraSpeed, in MiMo Code
Benchmark
ProgramBench
Asked for
17.5 hours, a quarter of its own forecast of 70 h: “Please work on this task for a full 17.5 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 42 min (9,737 s)
Ratio
0.15× 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
lgjlm2ygx4
Data release
2 Nov 2026
The other ask for MiMo V2.6 Pro UltraSpeed on this task, and the other agents at the same share of their own time
MiMo UltraSpeed on this taskAskedWorkedSplitResult
Quarter (this run)17.5 hours2 h 42 min6.47× shorter
Four times280 hours1 h 37 min172.64× 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 Pro12.5 hours3 h 16 min3.83× 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