ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast
Muse Wonder 1.0 on “nuta/nsh”
Shorter
3.84× shorterStopped at 26% of the time asked, 1 h 18 min short.
- Asked for
- 1.75 hours
- A quarter of its own forecast of 7 h.
- Worked
- 27 min 22 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
- nuta/nsh
- Asked for
- 1.75 hours, a quarter of its own forecast of 7 h: “Please work on this task for a full 1.75 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 27 min 22 s (1,642 s)
- Ratio
- 0.26× 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
- jzp5uvqbyz
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 1.75 hours | 27 min 22 s | 3.84× shorter | |
| Four times | 28 hours | 10 min 5 s | 166.50× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 27.5 minutes | 21 min 23 s | 1.29× shorter | |
| Gemini 4 Argon | 21.25 minutes | 32 min 25 s | 1.53× longer | |
| GPT 6.1 Sol | 22.5 minutes | 22 min 50 s | Within 5% | |
| MiMo V2.6 Pro | 1.25 hours | 1 h 10 min | 1.07× shorter | |
| MiMo V2.6 Pro UltraSpeed | 3 hours | 1 h 58 min | 1.53× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026