AssistantBench, AgentTime v1.1, asked for a quarter of its own forecast

MiMo V2.6 Pro on “AssistantBench validation task 6”

Longer

4.23× longer

Worked 323% past the request, 24 min 14 s over.

Asked for
7.5 minutes
A quarter of its own forecast of 30 min.
Worked
31 min 44 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
7.5 minutes, a quarter of its own forecast of 30 min: “Please work on this task for a full 7.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
31 min 44 s (1,904 s)
Ratio
4.23× 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
rrxi2ytenz
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
Quarter (this run)7.5 minutes31 min 44 s4.23× longer
Four times120 minutes2 h 2 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.53.25 minutes6 min 31 s2.01× longer
Gemini 4 Argon1.25 minutes1 min 35 s1.26× longer
GPT 6.1 Sol3 minutes3 min 24 s1.13× longer
MiMo V2.6 Pro UltraSpeed3.75 minutes29 min 48 s7.95× longer
Muse Wonder 1.05 minutes7 min 35 s1.52× longer

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)