ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast
Muse Wonder 1.0 on “cweill/gotests”
Shorter
4.91× shorterStopped at 20% of the time asked, 56 min 52 s short.
- Asked for
- 1.19 hours
- A quarter of its own forecast of 4 h 45 min.
- Worked
- 14 min 32 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
- cweill/gotests
- Asked for
- 1.19 hours, a quarter of its own forecast of 4 h 45 min: “Please work on this task for a full 1.19 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 14 min 32 s (872 s)
- Ratio
- 0.20× 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
- fnd6n4ytsb
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 1.19 hours | 14 min 32 s | 4.91× shorter | |
| Four times | 19 hours | no run | ||
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 35 minutes | 13 min 49 s | 2.53× shorter | |
| Gemini 4 Argon | 16.25 minutes | 35 min 31 s | 2.19× longer | |
| GPT 6.1 Sol | 15 minutes | 15 min 25 s | Within 5% | |
| MiMo V2.6 Pro | 1.75 hours | 1 h 12 min | 1.46× shorter | |
| MiMo V2.6 Pro UltraSpeed | 2.5 hours | 1 h 13 min | 2.06× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026