DeepSWE v1.1, AgentTime v1.1, asked for a quarter of its own forecast

Muse Wonder 1.0 on “Add worktree merge conflict handling”

Shorter

4.39× shorter

Stopped at 23% of the time asked, 34 min 46 s short.

Asked for
45 minutes
A quarter of its own forecast of 3 h.
Worked
10 min 14 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
45 minutes, a quarter of its own forecast of 3 h: “Please work on this task for a full 45 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 min 14 s (614 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
ikxaw6szvk
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)45 minutes10 min 14 s4.39× shorter
Four times720 minutes6 min 16 s114.83× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.510 minutes22 min 52 s2.29× longer
Gemini 4 Argon5.5 minutes34 min 29 s6.27× longer
GPT 6.1 Sol16.25 minutes16 min 37 sWithin 5%
MiMo V2.6 Pro1.125 hours23 min 56 s2.82× shorter
MiMo V2.6 Pro UltraSpeed1 hour11 min 49 s5.08× shorter

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

Data and citation

Upstream: Huang et al., 2026