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

Muse Wonder 1.0 on “Add worktree merge conflict handling”

Shorter

114.83× shorter

Stopped at 1% of the time asked, 11 h 54 min short.

Asked for
720 minutes
Four times its own forecast of 3 h.
Worked
6 min 16 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
720 minutes, four times its own forecast of 3 h: “Please work on this task for a full 720 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
6 min 16 s (376 s)
Ratio
0.01× 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
6or4yvs7a2
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
Quarter45 minutes10 min 14 s4.39× shorter
Four times (this run)720 minutes6 min 16 s114.83× shorter
Other agents, four times their own forecast
Claude Opus 5.5160 minutes2 h 15 min1.18× shorter
Gemini 4 Argon88 minutes1 h 1 min1.44× shorter
GPT 6.1 Sol260 minutes4 h 21 minWithin 5%
MiMo V2.6 Pro18 hours36 min 41 s29.44× shorter
MiMo V2.6 Pro UltraSpeed16 hours24 min 22 s39.41× shorter

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

Data and citation

Upstream: Huang et al., 2026