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

GPT 6.1 Sol on “Execute every task in a camping project across shopping, expenses, payments, invitations, and task closeout”

Within 5%

Within 5%

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

Asked for
72 minutes
Four times its own forecast of 18 min.
Worked
1 h 12 min
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
72 minutes, four times its own forecast of 18 min: “Please work on this task for a full 72 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 12 min (4,346 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
e4n4pt4dmc
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
Quarter4.5 minutes4 min 55 s1.09× longer
Four times (this run)72 minutes1 h 12 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.580 minutes17 min 32 s4.56× shorter
Gemini 4 Argon24 minutes48 min2.00× longer
MiMo V2.6 Pro140 minutes2 h 20 minWithin 5%
MiMo V2.6 Pro UltraSpeed112 minutes13 min 26 s8.34× shorter
Muse Wonder 1.0300 minutes11 min 37 s25.82× shorter

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

Data and citation

Upstream: Trivedi et al., 2024 (ACL)