Sakana ALE-Bench, AgentTime v1.1, asked for a quarter of its own forecast
Muse Wonder 1.0 on “AtCoder Heuristic Contest 26”
Shorter
14.22× shorterStopped at 7% of the time asked, 27 min 53 s short.
- Asked for
- 30 minutes
- A quarter of its own forecast of 2 h.
- Worked
- 2 min 7 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
- Sakana ALE-Bench
- Asked for
- 30 minutes, a quarter of its own forecast of 2 h: “Please work on this task for a full 30 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 min 7 s (127 s)
- Ratio
- 0.07× 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
- 6d7g23imao
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 30 minutes | 2 min 7 s | 14.22× shorter | |
| Four times | 480 minutes | 19 min 16 s | 24.92× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 11.25 minutes | 4 min 34 s | 2.47× shorter | |
| Gemini 4 Argon | 8.75 minutes | 8 min 56 s | Within 5% | |
| GPT 6.1 Sol | 6.25 minutes | 6 min 26 s | Within 5% | |
| MiMo V2.6 Pro | 1.25 hours | 54 min 24 s | 1.38× shorter | |
| MiMo V2.6 Pro UltraSpeed | 1.125 hours | 54 min 54 s | 1.23× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025