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

Muse Wonder 1.0 on “AssistantBench validation task 17”

Within 5%

Within 5%

Worked 101% of the time asked, within 5% of it.

Asked for
80 minutes
Four times its own forecast of 20 min.
Worked
1 h 21 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 21 min (4,870 s)
Ratio
1.01× 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
pm5z4ujhts
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 minutes10 min 40 s2.13× longer
Four times (this run)80 minutes1 h 21 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.528 minutes28 min 44 sWithin 5%
Gemini 4 Argon840 seconds14 min 39 sWithin 5%
GPT 6.1 Sol24 minutes24 min 41 sWithin 5%
MiMo V2.6 Pro100 minutes23 min 44 s4.21× shorter
MiMo V2.6 Pro UltraSpeed100 minutes13 min 48 s7.25× shorter

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

Data and citation

Upstream: Yoran et al., 2024 (EMNLP)