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 27”

Longer

8.33× longer

Worked 733% past the request, 5 min 30 s over.

Asked for
45 seconds
A quarter of its own forecast of 3 min.
Worked
6 min 15 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
45 seconds, a quarter of its own forecast of 3 min: “Please work on this task for a full 45 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
6 min 15 s (375 s)
Ratio
8.33× 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
7afgea5ufr
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)45 seconds6 min 15 s8.33× longer
Four times720 seconds12 min 12 sWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.51.5 minutes32 min 31 s21.67× longer
Gemini 4 Argon18 seconds38 min 34 s128.54× longer
MiMo V2.6 Pro3 minutes1 h 9 min22.98× longer
MiMo V2.6 Pro UltraSpeed2.75 minutes6 min 43 s2.44× longer
Muse Wonder 1.01 minute6 min 4 s6.06× longer

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

Data and citation

Upstream: Phan et al., 2025