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

MiMo V2.6 Pro on “AssistantBench validation task 16”

Shorter

1.92× shorter

Stopped at 52% of the time asked, 30 min 35 s short.

Asked for
64 minutes
Four times its own forecast of 16 min.
Worked
33 min 25 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
64 minutes, four times its own forecast of 16 min: “Please work on this task for a full 64 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
33 min 25 s (2,005 s)
Ratio
0.52× 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
i4glhninpi
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
Quarter4 minutes11 min 32 s2.88× longer
Four times (this run)64 minutes33 min 25 s1.92× shorter
Other agents, four times their own forecast
Claude Opus 5.548 minutes22 min 13 s2.16× shorter
Gemini 4 Argon840 seconds14 min 39 sWithin 5%
GPT 6.1 Sol36 minutes37 min 5 sWithin 5%
MiMo V2.6 Pro UltraSpeed120 minutes13 min 27 s8.92× shorter
Muse Wonder 1.056 minutes57 min 8 sWithin 5%

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)