CORE-Bench v1.1, AgentTime v1.1, asked for a quarter of its own forecast
Muse Wonder 1.0 on “Human Activities Recognition on PAMAP2 dataset using Random Forest”
Shorter
3.37× shorterStopped at 30% of the time asked, 6 min 9 s short.
- Asked for
- 8.75 minutes
- A quarter of its own forecast of 35 min.
- Worked
- 2 min 36 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
- CORE-Bench v1.1
- Asked for
- 8.75 minutes, a quarter of its own forecast of 35 min: “Please work on this task for a full 8.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 min 36 s (156 s)
- Ratio
- 0.30× 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
- 4wgo5c7vow
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 8.75 minutes | 2 min 36 s | 3.37× shorter | |
| Four times | 140 minutes | 31 min 2 s | 4.51× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 5 minutes | 12 min 3 s | 2.41× longer | |
| Gemini 4 Argon | 2 minutes | 3 min 25 s | 1.71× longer | |
| GPT 6.1 Sol | 11.25 minutes | 11 min 35 s | Within 5% | |
| MiMo V2.6 Pro | 15 minutes | 2 min 56 s | 5.12× shorter | |
| MiMo V2.6 Pro UltraSpeed | 17.5 minutes | 9 min 4 s | 1.93× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026