OSWorld 2.0, AgentTime v1.1, asked for a quarter of its own forecast
MiMo V2.6 Pro on “FreeCAD bracket”
Longer
1.93× longerWorked 93% past the request, 17 min 29 s over.
- Asked for
- 18.75 minutes
- A quarter of its own forecast of 1 h 15 min.
- Worked
- 36 min 14 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- MiMo V2.6 Pro, in MiMo Code
- Benchmark
- OSWorld 2.0
- Task
- FreeCAD bracket
- Asked for
- 18.75 minutes, a quarter of its own forecast of 1 h 15 min: “Please work on this task for a full 18.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 36 min 14 s (2,174 s)
- Ratio
- 1.93× 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
- bzmao3o3ms
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 18.75 minutes | 36 min 14 s | 1.93× longer | |
| Four times | 300 minutes | 4 h 39 min | 1.07× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 11.25 minutes | 11 min 8 s | Within 5% | |
| Gemini 4 Argon | 6.5 minutes | 1 h 8 min | 10.51× longer | |
| GPT 6.1 Sol | 13.75 minutes | 14 min 42 s | 1.07× longer | |
| MiMo V2.6 Pro UltraSpeed | 11.25 minutes | 12 min 22 s | 1.10× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026