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

Claude Opus 5.5 on “Humanity's Last Exam item 34”

Longer

1.09× longer

Worked 9% past the request, 3 min 37 s over.

Asked for
40 minutes
Four times its own forecast of 10 min.
Worked
43 min 37 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
40 minutes, four times its own forecast of 10 min: “Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
43 min 37 s (2,617 s)
Ratio
1.09× 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
qtrhp4bygg
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
Quarter2.5 minutes8 min 15 s3.30× longer
Four times (this run)40 minutes43 min 37 s1.09× longer
Other agents, four times their own forecast
Gemini 4 Argon600 seconds10 min 46 s1.08× longer
GPT 6.1 Sol32 minutes32 min 49 sWithin 5%
MiMo V2.6 Pro152 minutes1 h 8 min2.23× shorter
MiMo V2.6 Pro UltraSpeed180 minutes5 min 18 s33.92× shorter
Muse Wonder 1.020 minutes5 min 39 s3.54× shorter

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

Data and citation

Upstream: Phan et al., 2025