Agents' Last Exam, AgentTime v1.1, asked for four times its own forecast

Muse Wonder 1.0 on “Molecular Structure Plausibility”

Shorter

61.40× shorter

Stopped at 2% of the time asked, 2 h 18 min short.

Asked for
140 minutes
Four times its own forecast of 35 min.
Worked
2 min 17 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
140 minutes, four times its own forecast of 35 min: “Please work on this task for a full 140 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 min 17 s (137 s)
Ratio
0.02× 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
2qjol6u64d
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
Quarter8.75 minutes1 min 50 s4.76× shorter
Four times (this run)140 minutes2 min 17 s61.40× shorter
Other agents, four times their own forecast
Claude Opus 5.560 minutes28 min 27 s2.11× shorter
Gemini 4 Argon32 minutes33 min 50 s1.06× longer
GPT 6.1 Sol48 minutes48 min 37 sWithin 5%
MiMo V2.6 Pro140 minutes18 min 16 s7.67× shorter
MiMo V2.6 Pro UltraSpeed160 minutes4 min 7 s38.93× shorter

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

Data and citation

Upstream: Sun et al., 2026