OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “FreeCAD bracket”
Shorter
5.26× shorterStopped at 19% of the time asked, 2 h 58 min short.
- Asked for
- 220 minutes
- Four times its own forecast of 55 min.
- Worked
- 41 min 52 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- OSWorld 2.0
- Task
- FreeCAD bracket
- Asked for
- 220 minutes, four times its own forecast of 55 min: “Please work on this task for a full 220 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 41 min 52 s (2,512 s)
- Ratio
- 0.19× 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
- hf5oyc66ao
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 13.75 minutes | 14 min 42 s | 1.07× longer | |
| Four times (this run) | 220 minutes | 41 min 52 s | 5.26× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 180 minutes | 3 h 58 min | 1.32× longer | |
| Gemini 4 Argon | 104 minutes | 1 h 51 min | 1.07× longer | |
| MiMo V2.6 Pro | 300 minutes | 4 h 39 min | 1.07× shorter | |
| MiMo V2.6 Pro UltraSpeed | 180 minutes | 1 h 49 min | 1.66× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026