YC-Bench, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Run the current one-year startup simulation, official seed 3”
Shorter
23.29× shorterStopped at 4% of the time asked, 7 h 39 min short.
- Asked for
- 480 minutes
- Four times its own forecast of 2 h.
- Worked
- 20 min 37 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
- YC-Bench
- Asked for
- 480 minutes, four times its own forecast of 2 h: “Please work on this task for a full 480 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 20 min 37 s (1,237 s)
- Ratio
- 0.04× 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
- iyz6mz63r6
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 30 minutes | no run | ||
| Four times (this run) | 480 minutes | 20 min 37 s | 23.29× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 560 minutes | 2 h 7 min | 4.40× shorter | |
| Gemini 4 Argon | 140 minutes | 2 h 54 min | 1.24× longer | |
| GPT 6.1 Sol | 220 minutes | 3 h 39 min | Within 5% | |
| MiMo V2.6 Pro | 360 minutes | 1 h 53 min | 3.20× shorter | |
| MiMo V2.6 Pro UltraSpeed | 360 minutes | 40 min 21 s | 8.92× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: He et al., 2026