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

MiMo V2.6 Pro on “johnkerl/miller”

Shorter

2.62× shorter

Stopped at 38% of the time asked, 1 h 33 min short.

Asked for
2.5 hours
A quarter of its own forecast of 10 h.
Worked
57 min 20 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
ProgramBench
Asked for
2.5 hours, a quarter of its own forecast of 10 h: “Please work on this task for a full 2.5 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
57 min 20 s (3,440 s)
Ratio
0.38× 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
buzjeikeqy
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)2.5 hours57 min 20 s2.62× shorter
Four times40 hours54 min 12 s44.28× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.51.25 hours26 min 57 s2.78× shorter
Gemini 4 Argon30 minutes46 min 32 s1.55× longer
GPT 6.1 Sol30 minutes30 min 28 sWithin 5%
MiMo V2.6 Pro UltraSpeed10 hours1 h 8 min8.79× shorter
Muse Wonder 1.04.58 hours1 h 46 min2.59× shorter

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

Data and citation

Upstream: Yang et al., 2026