PPTArena, AgentTime v1.1, asked for four times its own forecast

GPT 6.1 Sol on “Swimlane process diagram”

Within 5%

Within 5%

Worked 102% of the time asked, within 5% of it.

Asked for
34 minutes
Four times its own forecast of 8 min 30 s.
Worked
34 min 35 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
PPTArena
Asked for
34 minutes, four times its own forecast of 8 min 30 s: “Please work on this task for a full 34 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
34 min 35 s (2,075 s)
Ratio
1.02× 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
nrplk3qlai
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
Quarter2.125 minutes2 min 17 s1.07× longer
Four times (this run)34 minutes34 min 35 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.548 minutes18 min 59 s2.53× shorter
Gemini 4 Argon24 minutes22 min 59 sWithin 5%
MiMo V2.6 Pro80 minutes20 min 53 s3.83× shorter
MiMo V2.6 Pro UltraSpeed88 minutes16 min 58 s5.19× shorter
Muse Wonder 1.068 minutes58 s70.83× shorter

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

Data and citation