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

Muse Wonder 1.0 on “AssistantBench validation task 18”

Longer

1.91× longer

Worked 91% past the request, 5 min over.

Asked for
5.5 minutes
A quarter of its own forecast of 22 min.
Worked
10 min 30 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
5.5 minutes, a quarter of its own forecast of 22 min: “Please work on this task for a full 5.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 min 30 s (630 s)
Ratio
1.91× 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
3rsqgf62nd
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)5.5 minutes10 min 30 s1.91× longer
Four times88 minutes1 h 29 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.53.75 minutes13 min 31 s3.60× longer
Gemini 4 Argon2.5 minutes7 min 8 s2.85× longer
GPT 6.1 Sol5.5 minutes14 min 34 s2.65× longer
MiMo V2.6 Pro6.25 minutes32 min 28 s5.19× longer
MiMo V2.6 Pro UltraSpeed7.5 minutes26 min 28 s3.53× longer

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)