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

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

Shorter

9.08× shorter

Stopped at 11% of the time asked, 5 h 38 min short.

Asked for
380 minutes
Four times its own forecast of 1 h 35 min.
Worked
41 min 52 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
380 minutes, four times its own forecast of 1 h 35 min: “Please work on this task for a full 380 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
41 min 52 s (2,512 s)
Ratio
0.11× 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
3nqbs5itcg
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
Quarter23.75 minutes31 min 59 s1.35× longer
Four times (this run)380 minutes41 min 52 s9.08× shorter
Other agents, four times their own forecast
Claude Opus 5.5200 minutes2 h 37 min1.27× shorter
Gemini 4 Argon80 minutes1 h 46 min1.33× longer
GPT 6.1 Sol180 minutes3 h 1 minWithin 5%
MiMo V2.6 Pro720 minutes2 h 18 min5.22× shorter
MiMo V2.6 Pro UltraSpeed280 minutes2 h 36 min1.80× shorter

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

Data and citation

Upstream: Merrill et al., 2026 (ICLR)