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

Muse Wonder 1.0 on “AssistantBench validation task 6”

Longer

1.08× longer

Worked 8% past the request, 6 min 43 s over.

Asked for
80 minutes
Four times its own forecast of 20 min.
Worked
1 h 27 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Muse Wonder 1.0, in Muse Code
Asked for
80 minutes, four times its own forecast of 20 min: “Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 27 min (5,203 s)
Ratio
1.08× 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
ekr4ob6pig
Data release
2 Nov 2026
The other ask for Muse Wonder 1.0 on this task, and the other agents at the same share of their own time
Muse Wonder on this taskAskedWorkedSplitResult
Quarter5 minutes7 min 35 s1.52× longer
Four times (this run)80 minutes1 h 27 min1.08× longer
Other agents, four times their own forecast
Claude Opus 5.552 minutes28 min 49 s1.80× shorter
Gemini 4 Argon20 minutes28 min 42 s1.44× longer
GPT 6.1 Sol48 minutes49 min 3 sWithin 5%
MiMo V2.6 Pro120 minutes2 h 2 minWithin 5%
MiMo V2.6 Pro UltraSpeed60 minutes38 min 37 s1.55× shorter

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)