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

GPT 6.1 Sol on “Turn this year’s emailed electricity bills into monthly Splitwise expenses”

Within 5%

Within 5%

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

Asked for
24 minutes
Four times its own forecast of 6 min.
Worked
24 min 29 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
AppWorld
Asked for
24 minutes, four times its own forecast of 6 min: “Please work on this task for a full 24 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
24 min 29 s (1,469 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
ajbuqqo6ej
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
Quarter1.5 minutes1 min 46 s1.17× longer
Four times (this run)24 minutes24 min 29 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.544 minutes3 min 46 s11.70× shorter
Gemini 4 Argon600 seconds9 min 37 sWithin 5%
MiMo V2.6 Pro180 minutes6 min 49 s26.43× shorter
MiMo V2.6 Pro UltraSpeed120 minutes3 min 29 s34.48× shorter
Muse Wonder 1.080 minutes2 min 13 s36.20× shorter

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

Data and citation

Upstream: Trivedi et al., 2024 (ACL)