CORE-Bench v1.1, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Run a continuous-time intelligent-reflecting-surface propagation model”
Shorter
40.27× shorterStopped at 2% of the time asked, 1 h 57 min short.
- Asked for
- 120 minutes
- Four times its own forecast of 30 min.
- Worked
- 2 min 59 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
- 120 minutes, four times its own forecast of 30 min: “Please work on this task for a full 120 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 min 59 s (179 s)
- Ratio
- 0.02× 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
- bgijgpftoh
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 7.5 minutes | 9 min 13 s | 1.23× longer | |
| Four times (this run) | 120 minutes | 2 min 59 s | 40.27× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 48 minutes | 23 min 41 s | 2.03× shorter | |
| Gemini 4 Argon | 840 seconds | 16 min 22 s | 1.17× longer | |
| GPT 6.1 Sol | 40 minutes | 40 min 58 s | Within 5% | |
| MiMo V2.6 Pro | 180 minutes | 23 min 2 s | 7.81× shorter | |
| MiMo V2.6 Pro UltraSpeed | 240 minutes | 17 min 41 s | 13.57× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026