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

Claude Opus 5.5 on “Humanity's Last Exam item 35”

Longer

1.18× longer

Worked 18% past the request, 44 s over.

Asked for
240 seconds
Four times its own forecast of 1 min.
Worked
4 min 44 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Claude Opus 5.5, in Claude Code
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 44 s (284 s)
Ratio
1.18× 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
adoo6rb27b
Data release
2 Nov 2026
The other ask for Claude Opus 5.5 on this task, and the other agents at the same share of their own time
Opus 5.5 on this taskAskedWorkedSplitResult
Quarter15 seconds52 s3.49× longer
Four times (this run)240 seconds4 min 44 s1.18× longer
Other agents, four times their own forecast
Gemini 4 Argon120 seconds2 min 23 s1.19× longer
GPT 6.1 Sol120 seconds2 min 9 s1.07× longer
MiMo V2.6 Pro480 seconds1 min 47 s4.49× shorter
MiMo V2.6 Pro UltraSpeed20 minutes22 s55.05× shorter
Muse Wonder 1.0120 seconds1 min 1 s1.98× shorter

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

Data and citation

Upstream: Phan et al., 2025