Sakana ALE-Bench, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “AtCoder Heuristic Contest 39”
Shorter
77.28× shorterStopped at 1% of the time asked, 10 h 51 min short.
- Asked for
- 660 minutes
- Four times its own forecast of 2 h 45 min.
- Worked
- 8 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
- Sakana ALE-Bench
- Asked for
- 660 minutes, four times its own forecast of 2 h 45 min: “Please work on this task for a full 660 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 8 min 32 s (512 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
- vc4gsykqq5
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 41.25 minutes | 2 min 35 s | 15.99× shorter | |
| Four times (this run) | 660 minutes | 8 min 32 s | 77.28× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 240 minutes | 3 h 19 min | 1.21× shorter | |
| Gemini 4 Argon | 180 minutes | 3 min 13 s | 55.90× shorter | |
| GPT 6.1 Sol | 140 minutes | 2 h 21 min | Within 5% | |
| MiMo V2.6 Pro | 16 hours | 1 h 1 min | 15.81× shorter | |
| MiMo V2.6 Pro UltraSpeed | 20 hours | 3 h 53 min | 5.15× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Imajuku et al., 2025