Sakana ALE-Bench, AgentTime v1.1, asked for four times its own forecast

MiMo V2.6 Pro on “AtCoder Heuristic Contest 26”

Shorter

10.84× shorter

Stopped at 9% of the time asked, 18 h 9 min short.

Asked for
20 hours
Four times its own forecast of 5 h.
Worked
1 h 51 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
MiMo V2.6 Pro, in MiMo Code
Asked for
20 hours, four times its own forecast of 5 h: “Please work on this task for a full 20 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 51 min (6,640 s)
Ratio
0.09× 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
k37zbyrfzq
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
Quarter1.25 hours54 min 24 s1.38× shorter
Four times (this run)20 hours1 h 51 min10.84× shorter
Other agents, four times their own forecast
Claude Opus 5.5180 minutes1 h 7 min2.68× shorter
Gemini 4 Argon140 minutes2 h 21 minWithin 5%
GPT 6.1 Sol100 minutes1 h 41 minWithin 5%
MiMo V2.6 Pro UltraSpeed18 hours46 min 42 s23.13× shorter
Muse Wonder 1.0480 minutes19 min 16 s24.92× shorter

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

Data and citation

Upstream: Imajuku et al., 2025