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

GPT 6.1 Sol on “Apple FY2024 Balance Sheet Reconstruction”

Within 5%

Within 5%

Worked 104% of the time asked, within 5% of it.

Asked for
600 seconds
Four times its own forecast of 2 min 30 s.
Worked
10 min 23 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
600 seconds, four times its own forecast of 2 min 30 s: “Please work on this task for a full 600 seconds. Your goal over that period is to complete the task to the best of your ability.”
Worked
10 min 23 s (623 s)
Ratio
1.04× 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
klaflap3ok
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
Quarter37.5 seconds59 s1.58× longer
Four times (this run)600 seconds10 min 23 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.524 minutes9 min 8 s2.63× shorter
Gemini 4 Argon480 seconds3 min 6 s2.58× shorter
MiMo V2.6 Pro48 minutes4 min 43 s10.19× shorter
MiMo V2.6 Pro UltraSpeed40 minutes2 min 30 s16.00× shorter
Muse Wonder 1.032 minutes1 min 6 s29.09× shorter

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

Data and citation

Upstream: Sun et al., 2026