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

MiMo V2.6 Pro UltraSpeed on “AssistantBench validation task 14”

Shorter

4.42× shorter

Stopped at 23% of the time asked, 55 min 42 s short.

Asked for
72 minutes
Four times its own forecast of 18 min.
Worked
16 min 18 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
Asked for
72 minutes, four times its own forecast of 18 min: “Please work on this task for a full 72 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
16 min 18 s (978 s)
Ratio
0.23× 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
uqcq2bsxoh
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
Quarter4.5 minutes4 min 44 s1.05× longer
Four times (this run)72 minutes16 min 18 s4.42× shorter
Other agents, four times their own forecast
Claude Opus 5.548 minutes41 min 57 s1.14× shorter
Gemini 4 Argon24 minutes24 min 50 sWithin 5%
GPT 6.1 Sol88 minutes1 h 29 minWithin 5%
MiMo V2.6 Pro88 minutes36 min 3 s2.44× shorter
Muse Wonder 1.088 minutes41 min 46 s2.11× shorter

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)