OSWorld 2.0, AgentTime v1.1, asked for a quarter of its own forecast
GPT 6.1 Sol on “GeoGebra vase and volume”
Longer
1.18× longerWorked 18% past the request, 1 min 6 s over.
- Asked for
- 6.25 minutes
- A quarter of its own forecast of 25 min.
- Worked
- 7 min 21 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
- Asked for
- 6.25 minutes, a quarter of its own forecast of 25 min: “Please work on this task for a full 6.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 7 min 21 s (441 s)
- Ratio
- 1.18× 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
- 2ee7rwdx6l
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 6.25 minutes | 7 min 21 s | 1.18× longer | |
| Four times | 100 minutes | 1 h 2 min | 1.62× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 6.25 minutes | 7 min 19 s | 1.17× longer | |
| Gemini 4 Argon | 3.75 minutes | 24 min 1 s | 6.41× longer | |
| MiMo V2.6 Pro | 12.5 minutes | 56 min 32 s | 4.52× longer | |
| MiMo V2.6 Pro UltraSpeed | 12 minutes | 22 min 6 s | 1.84× longer | |
| Muse Wonder 1.0 | 15 minutes | 19 min 26 s | 1.30× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026