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

Muse Wonder 1.0 on “Reproduce article and script-availability results across linguistics”

Shorter

10.09× shorter

Stopped at 10% of the time asked, 3 h 54 min short.

Asked for
260 minutes
Four times its own forecast of 1 h 5 min.
Worked
25 min 46 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
260 minutes, four times its own forecast of 1 h 5 min: “Please work on this task for a full 260 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
25 min 46 s (1,546 s)
Ratio
0.10× 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
al7mfzpbe4
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
Quarter16.25 minutes1 h 6 min4.07× longer
Four times (this run)260 minutes25 min 46 s10.09× shorter
Other agents, four times their own forecast
Claude Opus 5.596 minutes14 min 29 s6.63× shorter
Gemini 4 Argon40 minutes7 min 24 s5.41× shorter
GPT 6.1 Sol88 minutes1 h 29 minWithin 5%
MiMo V2.6 Pro360 minutes36 min 8 s9.96× shorter
MiMo V2.6 Pro UltraSpeed160 minutes24 min 49 s6.45× shorter

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

Data and citation

Upstream: Nadgir et al., 2026