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

GPT 6.1 Sol on “Reconcile a camping checklist with commitments and buy the remaining supplies”

Within 5%

Within 5%

Worked 103% of the time asked, within 5% of it.

Asked for
30 minutes
Four times its own forecast of 7 min 30 s.
Worked
31 min 2 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
30 minutes, four times its own forecast of 7 min 30 s: “Please work on this task for a full 30 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
31 min 2 s (1,862 s)
Ratio
1.03× 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
wbmj7xba22
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
Quarter1.875 minutes2 min 8 s1.14× longer
Four times (this run)30 minutes31 min 2 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.548 minutes15 min 51 s3.03× shorter
Gemini 4 Argon600 seconds20 min2.00× longer
MiMo V2.6 Pro100 minutes1 h 40 minWithin 5%
MiMo V2.6 Pro UltraSpeed180 minutes26 min 22 s6.83× shorter
Muse Wonder 1.0120 minutes6 min 39 s18.05× shorter

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

Data and citation

Upstream: Trivedi et al., 2024 (ACL)