ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast
Muse Wonder 1.0 on “ariga/atlas”
Shorter
19.05× shorterStopped at 5% of the time asked, 4 h 16 min short.
- Asked for
- 4.5 hours
- A quarter of its own forecast of 18 h.
- Worked
- 14 min 10 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
- ariga/atlas
- Asked for
- 4.5 hours, a quarter of its own forecast of 18 h: “Please work on this task for a full 4.5 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 14 min 10 s (850 s)
- Ratio
- 0.05× 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
- tunqunhcrl
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 4.5 hours | 14 min 10 s | 19.05× shorter | |
| Four times | 72 hours | 2 min 10 s | 1990.78× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 52.5 minutes | 41 min 47 s | 1.26× shorter | |
| Gemini 4 Argon | 18.75 minutes | 16 min 59 s | 1.10× shorter | |
| GPT 6.1 Sol | 25 minutes | 25 min 25 s | Within 5% | |
| MiMo V2.6 Pro | 7.5 hours | 1 h 11 min | 6.31× shorter | |
| MiMo V2.6 Pro UltraSpeed | 5 hours | 44 min 7 s | 6.80× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026