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

MiMo V2.6 Pro UltraSpeed on “Add deterministic map conflict detection to Y.Map writes”

Shorter

26.37× shorter

Stopped at 4% of the time asked, 15 h 24 min short.

Asked for
16 hours
Four times its own forecast of 4 h.
Worked
36 min 24 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
16 hours, four times its own forecast of 4 h: “Please work on this task for a full 16 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
36 min 24 s (2,184 s)
Ratio
0.04× 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
3s664uamzc
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
Quarter1 hour11 min 55 s5.04× shorter
Four times (this run)16 hours36 min 24 s26.37× shorter
Other agents, four times their own forecast
Claude Opus 5.5220 minutes1 h 17 min2.88× shorter
Gemini 4 Argon88 minutes1 h 17 min1.14× shorter
GPT 6.1 Sol200 minutes3 h 20 minWithin 5%
MiMo V2.6 Pro600 minutes32 min 19 s18.56× shorter
Muse Wonder 1.0540 minutes5 min 1 s107.57× shorter

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

Data and citation

Upstream: Huang et al., 2026