PPTArena, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Coordinated category boards”
Shorter
121.52× shorterStopped at 1% of the time asked, 1 h 35 min short.
- Asked for
- 96 minutes
- Four times its own forecast of 24 min.
- Worked
- 47 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
- PPTArena
- Asked for
- 96 minutes, four times its own forecast of 24 min: “Please work on this task for a full 96 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 47 s (47 s)
- Ratio
- 0.01× 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
- odxjvknsdf
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 6 minutes | 1 min 10 s | 5.13× shorter | |
| Four times (this run) | 96 minutes | 47 s | 121.52× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 56 minutes | 17 min 50 s | 3.14× shorter | |
| Gemini 4 Argon | 44 minutes | 1 h 4 min | 1.45× longer | |
| GPT 6.1 Sol | 40 minutes | 40 min 35 s | Within 5% | |
| MiMo V2.6 Pro | 200 minutes | 25 min 50 s | 7.74× shorter | |
| MiMo V2.6 Pro UltraSpeed | 200 minutes | 12 min 7 s | 16.52× shorter | |
See it on the chart. Transcripts are not published yet.