CORE-Bench v1.1, AgentTime v1.1, asked for a quarter of its own forecast

Muse Wonder 1.0 on “Run a continuous-time intelligent-reflecting-surface propagation model”

Longer

1.23× longer

Worked 23% past the request, 1 min 43 s over.

Asked for
7.5 minutes
A quarter of its own forecast of 30 min.
Worked
9 min 13 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
7.5 minutes, a quarter of its own forecast of 30 min: “Please work on this task for a full 7.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 13 s (553 s)
Ratio
1.23× 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
buuw65lul5
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
Quarter (this run)7.5 minutes9 min 13 s1.23× longer
Four times120 minutes2 min 59 s40.27× shorter
Other agents, a quarter of their own forecast
Claude Opus 5.53 minutes24 min 57 s8.32× longer
Gemini 4 Argon52.5 seconds1 min 22 s1.55× longer
GPT 6.1 Sol2.5 minutes2 min 50 s1.13× longer
MiMo V2.6 Pro11.25 minutes19 min 2 s1.69× longer
MiMo V2.6 Pro UltraSpeed15 minutes10 min 59 s1.37× shorter

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

Data and citation

Upstream: Nadgir et al., 2026