Humanity's Last Exam, AgentTime v1.1, asked for a quarter of its own forecast

GPT 6.1 Sol on “Humanity's Last Exam item 39”

Longer

1.65× longer

Worked 65% past the request, 15 s over.

Asked for
22.5 seconds
A quarter of its own forecast of 1 min 30 s.
Worked
37 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
22.5 seconds, a quarter of its own forecast of 1 min 30 s: “Please work on this task for a full 22.5 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
37 s (37 s)
Ratio
1.65× 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
5wticpc4yr
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)22.5 seconds37 s1.65× longer
Four times360 seconds6 min 12 sWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.522.5 seconds54 s2.39× longer
Gemini 4 Argon6 seconds30 s4.93× longer
MiMo V2.6 Pro30 seconds3 min 20 s6.67× longer
MiMo V2.6 Pro UltraSpeed45 seconds44 sWithin 5%
Muse Wonder 1.015 seconds35 s2.36× longer

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

Data and citation

Upstream: Phan et al., 2025