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

MiMo V2.6 Pro UltraSpeed on “Add session bundle recording and replay to IPython”

Shorter

77.08× shorter

Stopped at 1% of the time asked, 12 h 10 min short.

Asked for
740 minutes
Four times its own forecast of 3 h 5 min.
Worked
9 min 36 s
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
DeepSWE v1.1
Asked for
740 minutes, four times its own forecast of 3 h 5 min: “Please work on this task for a full 740 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 36 s (576 s)
Ratio
0.01× 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
72mvvqosji
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
Quarter46.25 minutes6 min 29 s7.13× shorter
Four times (this run)740 minutes9 min 36 s77.08× shorter
Other agents, four times their own forecast
Claude Opus 5.5140 minutes1 h 7 min2.10× shorter
Gemini 4 Argon60 minutes53 min 53 s1.11× shorter
GPT 6.1 Sol160 minutes2 h 41 minWithin 5%
MiMo V2.6 Pro16 hours21 min 39 s44.34× shorter
Muse Wonder 1.0440 minutes9 min 9 s48.09× shorter

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

Data and citation

Upstream: Huang et al., 2026