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

Muse Wonder 1.0 on “tomlkit-toml-table-converters”

Shorter

31.80× shorter

Stopped at 3% of the time asked, 9 h 41 min short.

Asked for
600 minutes
Four times its own forecast of 2 h 30 min.
Worked
18 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
Benchmark
DeepSWE v1.1
Asked for
600 minutes, four times its own forecast of 2 h 30 min: “Please work on this task for a full 600 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
18 min 52 s (1,132 s)
Ratio
0.03× 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
crzkk33bki
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
Quarter37.5 minutes19 min 52 s1.89× shorter
Four times (this run)600 minutes18 min 52 s31.80× shorter
Other agents, four times their own forecast
Claude Opus 5.5160 minutes2 h 22 min1.13× shorter
Gemini 4 Argon72 minutes1 h 7 min1.07× shorter
GPT 6.1 Sol128 minutes2 h 9 minWithin 5%
MiMo V2.6 Pro480 minutes35 min 55 s13.37× shorter
MiMo V2.6 Pro UltraSpeed540 minutes11 min 14 s48.04× shorter

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

Data and citation

Upstream: Huang et al., 2026