CORE-Bench v1.1, AgentTime v1.1, asked for a quarter of its own forecast
Muse Wonder 1.0 on “Reproduce a 20 mm transducer-array characterization”
Shorter
7.81× shorterStopped at 13% of the time asked, 8 min 43 s short.
- Asked for
- 10 minutes
- A quarter of its own forecast of 40 min.
- Worked
- 1 min 17 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
- 10 minutes, a quarter of its own forecast of 40 min: “Please work on this task for a full 10 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 min 17 s (77 s)
- Ratio
- 0.13× 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
- qhiufoqdwr
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 10 minutes | 1 min 17 s | 7.81× shorter | |
| Four times | 160 minutes | 1 min 34 s | 102.56× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 3.25 minutes | 2 min 26 s | 1.33× shorter | |
| Gemini 4 Argon | 52.5 seconds | 28 min | 32.00× longer | |
| GPT 6.1 Sol | 3 minutes | 3 min 15 s | 1.08× longer | |
| MiMo V2.6 Pro | 20 minutes | 2 min 29 s | 8.03× shorter | |
| MiMo V2.6 Pro UltraSpeed | 20 minutes | 3 min 5 s | 6.47× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026