DeepSWE v1.1, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Add duration-aware sharding to Vitest”
Shorter
64.13× shorterStopped at 2% of the time asked, 8 h 52 min short.
- Asked for
- 540 minutes
- Four times its own forecast of 2 h 15 min.
- Worked
- 8 min 25 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
- 540 minutes, four times its own forecast of 2 h 15 min: “Please work on this task for a full 540 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 8 min 25 s (505 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
- cfidxqbn2r
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 33.75 minutes | 5 min 51 s | 5.77× shorter | |
| Four times (this run) | 540 minutes | 8 min 25 s | 64.13× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 180 minutes | 1 h 44 min | 1.73× shorter | |
| Gemini 4 Argon | 140 minutes | 33 min 22 s | 4.20× shorter | |
| GPT 6.1 Sol | 168 minutes | 2 h 49 min | Within 5% | |
| MiMo V2.6 Pro | 600 minutes | 27 min 57 s | 21.47× shorter | |
| MiMo V2.6 Pro UltraSpeed | 20 hours | 24 min 46 s | 48.45× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Huang et al., 2026