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

GPT 6.1 Sol on “Apply collaborator feedback to a shared road-trip playlist and close the task”

Within 5%

Within 5%

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

Asked for
22 minutes
Four times its own forecast of 5 min 30 s.
Worked
22 min 39 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
22 minutes, four times its own forecast of 5 min 30 s: “Please work on this task for a full 22 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
22 min 39 s (1,359 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
uaah22e43d
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
Quarter1.375 minutes1 min 37 s1.17× longer
Four times (this run)22 minutes22 min 39 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.528 minutes2 min 27 s11.43× shorter
Gemini 4 Argon600 seconds4 min 20 s2.31× shorter
MiMo V2.6 Pro100 minutes3 min 44 s26.74× shorter
MiMo V2.6 Pro UltraSpeed48 minutes2 min 22 s20.34× shorter
Muse Wonder 1.060 minutes59 s60.61× shorter

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

Data and citation

Upstream: Trivedi et al., 2024 (ACL)