ProgramBench, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “canop/broot”
Shorter
210.90× shorterStopped at 0% of the time asked, 59 h 43 min short.
- Asked for
- 60 hours
- Four times its own forecast of 15 h.
- Worked
- 17 min 4 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
- ProgramBench
- Task
- canop/broot
- Asked for
- 60 hours, four times its own forecast of 15 h: “Please work on this task for a full 60 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 17 min 4 s (1,024 s)
- Ratio
- 0.00× 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
- e3fy5xzgq6
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 3.75 hours | 21 min 1 s | 10.71× shorter | |
| Four times (this run) | 60 hours | 17 min 4 s | 210.90× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 840 minutes | 9 h 3 min | 1.55× shorter | |
| Gemini 4 Argon | 300 minutes | 1 h | 4.97× shorter | |
| GPT 6.1 Sol | 600 minutes | 10 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 168 hours | 1 h 14 min | 136.94× shorter | |
| MiMo V2.6 Pro UltraSpeed | 144 hours | 1 h 15 min | 114.50× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026