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

Muse Wonder 1.0 on “Repair a React lead form and its auditable CRM submission pipeline”

Shorter

4.30× shorter

Stopped at 23% of the time asked, 16 min 19 s short.

Asked for
21.25 minutes
A quarter of its own forecast of 1 h 25 min.
Worked
4 min 56 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
21.25 minutes, a quarter of its own forecast of 1 h 25 min: “Please work on this task for a full 21.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 min 56 s (296 s)
Ratio
0.23× 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
j2i5ojxrju
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)21.25 minutes4 min 56 s4.30× shorter
Four times340 minutes9 min 59 s34.03× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.511.25 minutes12 min 23 s1.10× longer
Gemini 4 Argon4.5 minutes14 min 56 s3.32× longer
GPT 6.1 Sol7.5 minutes7 min 44 sWithin 5%
MiMo V2.6 Pro52.5 minutes29 min 7 s1.80× shorter
MiMo V2.6 Pro UltraSpeed1 hour8 min 32 s7.03× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)