DeepSWE v1.1, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Add session bundle recording and replay to IPython”
Shorter
48.09× shorterStopped at 2% of the time asked, 7 h 11 min short.
- Asked for
- 440 minutes
- Four times its own forecast of 1 h 50 min.
- Worked
- 9 min 9 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
- DeepSWE v1.1
- Asked for
- 440 minutes, four times its own forecast of 1 h 50 min: “Please work on this task for a full 440 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 9 min 9 s (549 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
- nbzlynf75x
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 27.5 minutes | 11 min 11 s | 2.46× shorter | |
| Four times (this run) | 440 minutes | 9 min 9 s | 48.09× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 140 minutes | 1 h 7 min | 2.10× shorter | |
| Gemini 4 Argon | 60 minutes | 53 min 53 s | 1.11× shorter | |
| GPT 6.1 Sol | 160 minutes | 2 h 41 min | Within 5% | |
| MiMo V2.6 Pro | 16 hours | 21 min 39 s | 44.34× shorter | |
| MiMo V2.6 Pro UltraSpeed | 740 minutes | 9 min 36 s | 77.08× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Huang et al., 2026