OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “Shotcut montage project”
Shorter
4.38× shorterStopped at 23% of the time asked, 2 h 19 min short.
- Asked for
- 180 minutes
- Four times its own forecast of 45 min.
- Worked
- 41 min 8 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
- 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
- 41 min 8 s (2,468 s)
- Ratio
- 0.23× 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
- ocmcbmg5ii
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 11.25 minutes | 12 min 34 s | 1.12× longer | |
| Four times (this run) | 180 minutes | 41 min 8 s | 4.38× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 380 minutes | 53 min 42 s | 7.08× shorter | |
| Gemini 4 Argon | 88 minutes | 2 h 28 min | 1.68× longer | |
| MiMo V2.6 Pro | 480 minutes | 4 h 41 min | 1.71× shorter | |
| MiMo V2.6 Pro UltraSpeed | 320 minutes | 2 h 45 min | 1.94× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026