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

Muse Wonder 1.0 on “AssistantBench validation task 6”

Longer

1.52× longer

Worked 52% past the request, 2 min 35 s over.

Asked for
5 minutes
A quarter of its own forecast of 20 min.
Worked
7 min 35 s
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
5 minutes, a quarter of its own forecast of 20 min: “Please work on this task for a full 5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
7 min 35 s (455 s)
Ratio
1.52× 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
mhxkma437z
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
Quarter (this run)5 minutes7 min 35 s1.52× longer
Four times80 minutes1 h 27 min1.08× longer
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 Pro7.5 minutes31 min 44 s4.23× longer
MiMo V2.6 Pro UltraSpeed3.75 minutes29 min 48 s7.95× longer

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)