DeepSWE v1.1, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “Add session bundle recording and replay to IPython”

Shorter

48.09× shorter

Stopped at 2% of the time asked, 7 h 11 min short.

Asked for
440 minutes
Four times its own forecast of 1 h 50 min.
Worked
9 min 9 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Muse Wonder 1.0, in Muse Code
Benchmark
DeepSWE v1.1
Asked for
440 minutes, four times its own forecast of 1 h 50 min: “Please work on this task for a full 440 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 9 s (549 s)
Ratio
0.02× 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
nbzlynf75x
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
Quarter27.5 minutes11 min 11 s2.46× shorter
Four times (this run)440 minutes9 min 9 s48.09× shorter
Other agents, four times their own forecast
Claude Opus 5.5140 minutes1 h 7 min2.10× shorter
Gemini 4 Argon60 minutes53 min 53 s1.11× shorter
GPT 6.1 Sol160 minutes2 h 41 minWithin 5%
MiMo V2.6 Pro16 hours21 min 39 s44.34× shorter
MiMo V2.6 Pro UltraSpeed740 minutes9 min 36 s77.08× shorter

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

Data and citation

Upstream: Huang et al., 2026