OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “Invoices, photos, and email”
Within 5%
Within 5%Worked 102% of the time asked, within 5% of it.
- Asked for
- 180 minutes
- Four times its own forecast of 45 min.
- Worked
- 3 h 4 min
- 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
- 180 minutes, four times its own forecast of 45 min: “Please work on this task for a full 180 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 3 h 4 min (11,053 s)
- Ratio
- 1.02× 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
- ilkywphlod
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 11.25 minutes | 14 min 16 s | 1.27× longer | |
| Four times (this run) | 180 minutes | 3 h 4 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 160 minutes | 2 h 29 min | 1.07× shorter | |
| Gemini 4 Argon | 80 minutes | 2 h 1 min | 1.51× longer | |
| MiMo V2.6 Pro | 152 minutes | 2 h 29 min | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 280 minutes | 6 h 8 min | 1.31× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026