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

MiMo V2.6 Pro on “AtCoder Heuristic Contest 31”

Shorter

8.57× shorter

Stopped at 12% of the time asked, 15 h 17 min short.

Asked for
17.3 hours
Four times its own forecast of 4 h 20 min.
Worked
2 h 1 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
17.3 hours, four times its own forecast of 4 h 20 min: “Please work on this task for a full 17.3 hours. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 1 min (7,268 s)
Ratio
0.12× 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
y6n5fm3qe7
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
Quarter1.08 hours44 min1.47× shorter
Four times (this run)17.3 hours2 h 1 min8.57× shorter
Other agents, four times their own forecast
Claude Opus 5.5360 minutes5 h 2 min1.19× shorter
Gemini 4 Argon180 minutes21 min 31 s8.37× shorter
GPT 6.1 Sol200 minutes3 h 21 minWithin 5%
MiMo V2.6 Pro UltraSpeed20 hours2 h 48 min7.13× shorter
Muse Wonder 1.0680 minutes3 min 34 s191.01× shorter

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

Data and citation

Upstream: Imajuku et al., 2025