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

GPT 6.1 Sol on “Reconcile Venmo payments into Splitwise with attached receipts”

Within 5%

Within 5%

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

Asked for
30 minutes
Four times its own forecast of 7 min 30 s.
Worked
30 min 23 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
30 min 23 s (1,823 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
xwval7pte5
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 11 s1.17× longer
Four times (this run)30 minutes30 min 23 sWithin 5%
Other agents, four times their own forecast
Claude Opus 5.552 minutes2 min 31 s20.72× shorter
Gemini 4 Argon480 seconds6 min 38 s1.20× shorter
MiMo V2.6 Pro88 minutes4 min 55 s17.92× shorter
MiMo V2.6 Pro UltraSpeed72 minutes1 min 48 s40.00× shorter
Muse Wonder 1.0120 minutes1 min 8 s106.19× shorter

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

Data and citation

Upstream: Trivedi et al., 2024 (ACL)