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

GPT 6.1 Sol on “Future Contest 2022 Qual”

Within 5%

Within 5%

Worked 100% of the time asked, within 5% of it.

Asked for
160 minutes
Four times its own forecast of 40 min.
Worked
2 h 40 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Asked for
160 minutes, four times its own forecast of 40 min: “Please work on this task for a full 160 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 40 min (9,629 s)
Ratio
1.00× 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
kqd3bwa6vb
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
Quarter10 minutes10 min 11 sWithin 5%
Four times (this run)160 minutes2 h 40 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.5280 minutes2 h 33 min1.83× shorter
Gemini 4 Argon180 minutes2 h 59 minWithin 5%
MiMo V2.6 Pro700 minutes1 h 40 min7.00× shorter
MiMo V2.6 Pro UltraSpeed24 hours2 h 50 min8.46× shorter
Muse Wonder 1.0840 minutes37 min 48 s22.22× shorter

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

Data and citation

Upstream: Imajuku et al., 2025