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

Muse Wonder 1.0 on “Recalculate SA-CCR exposure, RWA, capital, and workbook evidence”

Shorter

5.01× shorter

Stopped at 20% of the time asked, 32 min 1 s short.

Asked for
40 minutes
A quarter of its own forecast of 2 h 40 min.
Worked
7 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
40 minutes, a quarter of its own forecast of 2 h 40 min: “Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
7 min 59 s (479 s)
Ratio
0.20× 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
ovk3vlwh33
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)40 minutes7 min 59 s5.01× shorter
Four times640 minutes5 min128.00× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.57.5 minutes12 min 47 s1.70× longer
Gemini 4 Argon4.5 minutes14 min 8 s3.14× longer
GPT 6.1 Sol5.5 minutes5 min 48 s1.05× longer
MiMo V2.6 Pro45 minutes22 min 14 s2.02× shorter
MiMo V2.6 Pro UltraSpeed23.75 minutes6 min 25 s3.71× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)