CORE-Bench v1.1, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “Reproduce a rockshelter chronology and archaeological materials analysis”

Shorter

13.48× shorter

Stopped at 7% of the time asked, 3 h 42 min short.

Asked for
240 minutes
Four times its own forecast of 1 h.
Worked
17 min 49 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Muse Wonder 1.0, in Muse Code
Asked for
240 minutes, four times its own forecast of 1 h: “Please work on this task for a full 240 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
17 min 49 s (1,069 s)
Ratio
0.07× 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
qlwj44zcrw
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
Quarter15 minutes28 min 58 s1.93× longer
Four times (this run)240 minutes17 min 49 s13.48× shorter
Other agents, four times their own forecast
Claude Opus 5.5160 minutes39 min 49 s4.02× shorter
Gemini 4 Argon60 minutes14 min 42 s4.08× shorter
GPT 6.1 Sol200 minutes3 h 21 minWithin 5%
MiMo V2.6 Pro420 minutes1 h 6 min6.32× shorter
MiMo V2.6 Pro UltraSpeed340 minutes36 min 21 s9.35× shorter

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

Data and citation

Upstream: Nadgir et al., 2026