OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro on “Radio bumper”
Within 5%
Within 5%Worked 99% of the time asked, within 5% of it.
- Asked for
- 128 minutes
- Four times its own forecast of 32 min.
- Worked
- 2 h 7 min
- 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
- Radio bumper
- Asked for
- 128 minutes, four times its own forecast of 32 min: “Please work on this task for a full 128 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 h 7 min (7,609 s)
- Ratio
- 0.99× 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
- eaf4virfhu
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 8 minutes | 1 h 16 min | 9.51× longer | |
| Four times (this run) | 128 minutes | 2 h 7 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 128 minutes | 1 h 44 min | 1.23× shorter | |
| Gemini 4 Argon | 60 minutes | 10 min 16 s | 5.85× shorter | |
| GPT 6.1 Sol | 140 minutes | 2 h 22 min | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 220 minutes | 24 min 45 s | 8.89× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026