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

GPT 6.1 Sol on “Future Contest 2022 Qual”

Within 5%

Within 5%

Worked 102% of the time asked, within 5% of it.

Asked for
10 minutes
A quarter of its own forecast of 40 min.
Worked
10 min 11 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Asked for
10 minutes, a quarter of its own forecast of 40 min: “Please work on this task for a full 10 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 min 11 s (611 s)
Ratio
1.02× 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
vnh6qcsj66
Data release
2 Nov 2026
The other ask for GPT 6.1 Sol on this task, and the other agents at the same share of their own time
Sol 6.1 on this taskAskedWorkedSplitResult
Quarter (this run)10 minutes10 min 11 sWithin 5%
Four times160 minutes2 h 40 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.517.5 minutes14 min 37 s1.20× shorter
Gemini 4 Argon11.25 minutes15 min 45 s1.40× longer
MiMo V2.6 Pro43.75 minutes1 h 20 min1.83× longer
MiMo V2.6 Pro UltraSpeed1.5 hours52 min 7 s1.73× shorter
Muse Wonder 1.052.5 minutes4 min 58 s10.58× shorter

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

Data and citation

Upstream: Imajuku et al., 2025