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

GPT 6.1 Sol on “Build a clean retail SQLite warehouse from messy inputs”

Within 5%

Within 5%

Worked 101% of the time asked, within 5% of it.

Asked for
64 minutes
Four times its own forecast of 16 min.
Worked
1 h 4 min
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Asked for
64 minutes, four times its own forecast of 16 min: “Please work on this task for a full 64 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 4 min (3,862 s)
Ratio
1.01× 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
eoaeb7b7f7
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
Quarter4 minutes4 min 19 s1.08× longer
Four times (this run)64 minutes1 h 4 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.5128 minutes39 min 37 s3.23× shorter
Gemini 4 Argon56 minutes14 min 58 s3.74× shorter
MiMo V2.6 Pro240 minutes7 min 13 s33.29× shorter
MiMo V2.6 Pro UltraSpeed248 minutes4 min 18 s57.67× shorter
Muse Wonder 1.0200 minutes1 min 8 s176.99× shorter

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

Data and citation

Upstream: Sun et al., 2026