ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast
Muse Wonder 1.0 on “jesseduffield/lazygit”
Shorter
6.53× shorterStopped at 15% of the time asked, 2 h 32 min short.
- Asked for
- 3 hours
- A quarter of its own forecast of 12 h.
- Worked
- 27 min 35 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
- Asked for
- 3 hours, a quarter of its own forecast of 12 h: “Please work on this task for a full 3 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 27 min 35 s (1,655 s)
- Ratio
- 0.15× 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
- vsrrv52g23
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 3 hours | 27 min 35 s | 6.53× shorter | |
| Four times | 48 hours | 13 min 56 s | 206.60× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 50 minutes | 9 min 56 s | 5.03× shorter | |
| Gemini 4 Argon | 21.25 minutes | 21 min 53 s | Within 5% | |
| GPT 6.1 Sol | 30 minutes | 30 min 21 s | Within 5% | |
| MiMo V2.6 Pro | 10 hours | 1 h 19 min | 7.58× shorter | |
| MiMo V2.6 Pro UltraSpeed | 3.75 hours | 1 h 13 min | 3.09× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026