OSWorld 2.0, AgentTime v1.1, asked for a quarter of its own forecast
GPT 6.1 Sol on “Reimbursement package”
Longer
1.11× longerWorked 11% past the request, 41 s over.
- Asked for
- 6.5 minutes
- A quarter of its own forecast of 26 min.
- Worked
- 7 min 11 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
- 6.5 minutes, a quarter of its own forecast of 26 min: “Please work on this task for a full 6.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 7 min 11 s (431 s)
- Ratio
- 1.11× 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
- mzx3z6o3uc
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 6.5 minutes | 7 min 11 s | 1.11× longer | |
| Four times | 104 minutes | 1 h 45 min | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 8.75 minutes | 10 min 11 s | 1.16× longer | |
| Gemini 4 Argon | 3 minutes | 31 min 7 s | 10.37× longer | |
| MiMo V2.6 Pro | 5 minutes | 44 min 32 s | 8.91× longer | |
| MiMo V2.6 Pro UltraSpeed | 5.5 minutes | 1 h 9 min | 12.56× longer | |
| Muse Wonder 1.0 | 8 minutes | 35 min 44 s | 4.47× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026