AppWorld, AgentTime v1.1, asked for a quarter of its own forecast

GPT 6.1 Sol on “Rebuild and send a drafted recommendation email from the user’s Spotify history”

Longer

1.12× longer

Worked 12% past the request, 12 s over.

Asked for
1.625 minutes
A quarter of its own forecast of 6 min 30 s.
Worked
1 min 49 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
1.625 minutes, a quarter of its own forecast of 6 min 30 s: “Please work on this task for a full 1.625 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 min 49 s (109 s)
Ratio
1.12× 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
btlzcx7smy
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
Quarter (this run)1.625 minutes1 min 49 s1.12× longer
Four times26 minutes26 min 35 sWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.52.25 minutes1 min 24 s1.61× shorter
Gemini 4 Argon37.5 seconds3 min 43 s5.94× longer
MiMo V2.6 Pro4 minutes4 min 13 s1.05× longer
MiMo V2.6 Pro UltraSpeed6.25 minutes1 min 39 s3.79× shorter
Muse Wonder 1.04.5 minutes3 min 58 s1.14× shorter

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

Data and citation

Upstream: Trivedi et al., 2024 (ACL)