AppWorld, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Build a recruiting CSV and archive each candidate’s attachments”
Shorter
53.73× shorterStopped at 2% of the time asked, 1 h 11 min short.
- Asked for
- 72 minutes
- Four times its own forecast of 18 min.
- Worked
- 1 min 20 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Muse Wonder 1.0, in Muse Code
- 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 min 20 s (80 s)
- Ratio
- 0.02× 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
- 3qlpxts7ro
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 4.5 minutes | 56 s | 4.79× shorter | |
| Four times (this run) | 72 minutes | 1 min 20 s | 53.73× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 44 minutes | 3 min 37 s | 12.15× shorter | |
| Gemini 4 Argon | 600 seconds | 20 min | 2.00× longer | |
| GPT 6.1 Sol | 24 minutes | 24 min 36 s | Within 5% | |
| MiMo V2.6 Pro | 120 minutes | 8 min 31 s | 14.08× shorter | |
| MiMo V2.6 Pro UltraSpeed | 40 minutes | 3 min 31 s | 11.40× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Trivedi et al., 2024 (ACL)