ProgramBench, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “tomarrell/wrapcheck”
Shorter
122.08× shorterStopped at 1% of the time asked, 19 h 50 min short.
- Asked for
- 20 hours
- Four times its own forecast of 5 h.
- Worked
- 9 min 50 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
- 20 hours, four times its own forecast of 5 h: “Please work on this task for a full 20 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 9 min 50 s (590 s)
- Ratio
- 0.01× 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
- 54wdck3pp3
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 1.25 hours | 19 min 51 s | 3.78× shorter | |
| Four times (this run) | 20 hours | 9 min 50 s | 122.08× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 300 minutes | 2 h 20 min | 2.14× shorter | |
| Gemini 4 Argon | 168 minutes | 3 min 24 s | 49.41× shorter | |
| GPT 6.1 Sol | 240 minutes | 4 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 24 hours | 1 h 26 min | 16.66× shorter | |
| MiMo V2.6 Pro UltraSpeed | 28 hours | 53 min 27 s | 31.43× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026