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

Muse Wonder 1.0 on “Add duration-aware sharding to Vitest”

Shorter

64.13× shorter

Stopped at 2% of the time asked, 8 h 52 min short.

Asked for
540 minutes
Four times its own forecast of 2 h 15 min.
Worked
8 min 25 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
540 minutes, four times its own forecast of 2 h 15 min: “Please work on this task for a full 540 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
8 min 25 s (505 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
cfidxqbn2r
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
Quarter33.75 minutes5 min 51 s5.77× shorter
Four times (this run)540 minutes8 min 25 s64.13× shorter
Other agents, four times their own forecast
Claude Opus 5.5180 minutes1 h 44 min1.73× shorter
Gemini 4 Argon140 minutes33 min 22 s4.20× shorter
GPT 6.1 Sol168 minutes2 h 49 minWithin 5%
MiMo V2.6 Pro600 minutes27 min 57 s21.47× shorter
MiMo V2.6 Pro UltraSpeed20 hours24 min 46 s48.45× shorter

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

Data and citation

Upstream: Huang et al., 2026