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

MiMo V2.6 Pro on “AssistantBench validation task 18”

Shorter

1.80× shorter

Stopped at 55% of the time asked, 44 min 32 s short.

Asked for
100 minutes
Four times its own forecast of 25 min.
Worked
55 min 28 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
100 minutes, four times its own forecast of 25 min: “Please work on this task for a full 100 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
55 min 28 s (3,328 s)
Ratio
0.55× 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
6fhucnrajo
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
Quarter6.25 minutes32 min 28 s5.19× longer
Four times (this run)100 minutes55 min 28 s1.80× shorter
Other agents, four times their own forecast
Claude Opus 5.560 minutes24 min 2 s2.50× shorter
Gemini 4 Argon40 minutes40 min 39 sWithin 5%
GPT 6.1 Sol88 minutes1 h 29 minWithin 5%
MiMo V2.6 Pro UltraSpeed120 minutes6 h3.00× longer
Muse Wonder 1.088 minutes1 h 29 minWithin 5%

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)