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

GPT 6.1 Sol on “Humanity's Last Exam item 37”

Within 5%

Within 5%

Worked 105% of the time asked, within 5% of it.

Asked for
240 seconds
Four times its own forecast of 1 min.
Worked
4 min 12 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
240 seconds, four times its own forecast of 1 min: “Please work on this task for a full 240 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 min 12 s (252 s)
Ratio
1.05× 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
6a2zxc36uw
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
Quarter15 seconds53 s3.55× longer
Four times (this run)240 seconds4 min 12 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.5360 seconds6 min 57 s1.16× longer
Gemini 4 Argon96 seconds1 min 51 s1.16× longer
MiMo V2.6 Pro240 seconds11 min 17 s2.82× longer
MiMo V2.6 Pro UltraSpeed20 minutes1 min 9 s17.34× shorter
Muse Wonder 1.0240 seconds1 min 36 s2.51× shorter

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

Data and citation

Upstream: Phan et al., 2025