Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “hof-topology-interpenetration”

Shorter

31.07× shorter

Stopped at 3% of the time asked, 12 h 16 min short.

Asked for
760 minutes
Four times its own forecast of 3 h 10 min.
Worked
24 min 28 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
760 minutes, four times its own forecast of 3 h 10 min: “Please work on this task for a full 760 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
24 min 28 s (1,468 s)
Ratio
0.03× 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
6zblupf7eg
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
Quarter47.5 minutes15 min 28 s3.07× shorter
Four times (this run)760 minutes24 min 28 s31.07× shorter
Other agents, four times their own forecast
Claude Opus 5.5200 minutes24 min 25 s8.19× shorter
Gemini 4 Argon112 minutes26 min 7 s4.29× shorter
GPT 6.1 Sol240 minutes4 h 1 minWithin 5%
MiMo V2.6 Pro18 hours1 h 17 min14.00× shorter
MiMo V2.6 Pro UltraSpeed28 hours28 min 29 s58.99× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)