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
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 4.5 minutes | 4 min 55 s | 1.09× longer | |
| Four times (this run) | 72 minutes | 1 h 12 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 80 minutes | 17 min 32 s | 4.56× shorter | |
| Gemini 4 Argon | 24 minutes | 48 min | 2.00× longer | |
| MiMo V2.6 Pro | 140 minutes | 2 h 20 min | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 112 minutes | 13 min 26 s | 8.34× shorter | |
| Muse Wonder 1.0 | 300 minutes | 11 min 37 s | 25.82× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Trivedi et al., 2024 (ACL)