Terminal-Bench 4.0, AgentTime v1.1, asked for a quarter of its own forecast

Muse Wonder 1.0 on “Train a lake-temperature profile model from sparse observations”

Longer

1.35× longer

Worked 35% past the request, 8 min 14 s over.

Asked for
23.75 minutes
A quarter of its own forecast of 1 h 35 min.
Worked
31 min 59 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
23.75 minutes, a quarter of its own forecast of 1 h 35 min: “Please work on this task for a full 23.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
31 min 59 s (1,919 s)
Ratio
1.35× 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
ix7ppptwws
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)23.75 minutes31 min 59 s1.35× longer
Four times380 minutes41 min 52 s9.08× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.512.5 minutes10 min 35 s1.18× shorter
Gemini 4 Argon5 minutes18 min 8 s3.63× longer
GPT 6.1 Sol11.25 minutes11 min 38 sWithin 5%
MiMo V2.6 Pro45 minutes1 h 13 min1.63× longer
MiMo V2.6 Pro UltraSpeed17.5 minutes25 min 19 s1.45× longer

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)