DeepSWE v1.1, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro UltraSpeed on “Add RFC 5545 timezone interoperability to dateutil recurrence parsing”
Shorter
64.71× shorterStopped at 2% of the time asked, 13 h 47 min short.
- Asked for
- 840 minutes
- Four times its own forecast of 3 h 30 min.
- Worked
- 12 min 59 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- MiMo V2.6 Pro UltraSpeed, in MiMo Code
- Benchmark
- DeepSWE v1.1
- Asked for
- 840 minutes, four times its own forecast of 3 h 30 min: “Please work on this task for a full 840 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 12 min 59 s (779 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
- lenxtt2srk
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 52.5 minutes | 7 min 46 s | 6.77× shorter | |
| Four times (this run) | 840 minutes | 12 min 59 s | 64.71× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 160 minutes | 2 h 2 min | 1.32× shorter | |
| Gemini 4 Argon | 100 minutes | 50 min | 2.00× shorter | |
| GPT 6.1 Sol | 140 minutes | 2 h 21 min | Within 5% | |
| MiMo V2.6 Pro | 340 minutes | 21 min 4 s | 16.14× shorter | |
| Muse Wonder 1.0 | 600 minutes | 15 min 32 s | 38.63× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Huang et al., 2026