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

MiMo V2.6 Pro on “Run a quantum measurement and tomography toolbox”

Shorter

24.02× shorter

Stopped at 4% of the time asked, 3 h 50 min short.

Asked for
240 minutes
Four times its own forecast of 1 h.
Worked
9 min 59 s
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
240 minutes, four times its own forecast of 1 h: “Please work on this task for a full 240 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 59 s (599 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
jktwwatoqw
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
Quarter15 minutes8 min 9 s1.84× shorter
Four times (this run)240 minutes9 min 59 s24.02× shorter
Other agents, four times their own forecast
Claude Opus 5.540 minutes7 min 40 s5.22× shorter
Gemini 4 Argon20 minutes21 min 11 s1.06× longer
GPT 6.1 Sol40 minutes40 min 29 sWithin 5%
MiMo V2.6 Pro UltraSpeed220 minutes5 min 59 s36.79× shorter
Muse Wonder 1.0192 minutes1 min 33 s123.87× shorter

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

Data and citation

Upstream: Nadgir et al., 2026