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

Muse Wonder 1.0 on “Add server-sent-event streaming endpoints to Effect HttpApi”

Shorter

28.55× shorter

Stopped at 4% of the time asked, 13 h 31 min short.

Asked for
840 minutes
Four times its own forecast of 3 h 30 min.
Worked
29 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
840 minutes, four times its own forecast of 3 h 30 min: “Please work on this task for a full 840 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
29 min 25 s (1,765 s)
Ratio
0.04× 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
rnqv65snzu
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
Quarter52.5 minutes39 min 16 s1.34× shorter
Four times (this run)840 minutes29 min 25 s28.55× shorter
Other agents, four times their own forecast
Claude Opus 5.5200 minutes2 h 37 min1.28× shorter
Gemini 4 Argon128 minutes1 h 6 min1.95× shorter
GPT 6.1 Sol280 minutes4 h 41 minWithin 5%
MiMo V2.6 Pro460 minutes41 min 15 s11.15× shorter
MiMo V2.6 Pro UltraSpeed720 minutes28 min 13 s25.51× shorter

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

Data and citation

Upstream: Huang et al., 2026