ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast
Muse Wonder 1.0 on “typst/typst”
Shorter
42.33× shorterStopped at 2% of the time asked, 7 h 19 min short.
- Asked for
- 7.5 hours
- A quarter of its own forecast of 30 h.
- Worked
- 10 min 38 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
- typst/typst
- Asked for
- 7.5 hours, a quarter of its own forecast of 30 h: “Please work on this task for a full 7.5 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 10 min 38 s (638 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
- vxazuqxiqn
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 7.5 hours | 10 min 38 s | 42.33× shorter | |
| Four times | 120 hours | 22 min 37 s | 318.30× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 1 hour | 17 min 34 s | 3.42× shorter | |
| Gemini 4 Argon | 27.5 minutes | 7 min 22 s | 3.73× shorter | |
| GPT 6.1 Sol | 26.25 minutes | 26 min 37 s | Within 5% | |
| MiMo V2.6 Pro | 5.25 hours | 2 h 25 min | 2.18× shorter | |
| MiMo V2.6 Pro UltraSpeed | 5 hours | 1 h 13 min | 4.12× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026