OSWorld 2.0, AgentTime v1.1, asked for a quarter of its own forecast
GPT 6.1 Sol on “Local event booking QA”
Longer
1.15× longerWorked 15% past the request, 1 min 21 s over.
- Asked for
- 8.75 minutes
- A quarter of its own forecast of 35 min.
- Worked
- 10 min 6 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
- 8.75 minutes, a quarter of its own forecast of 35 min: “Please work on this task for a full 8.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 10 min 6 s (606 s)
- Ratio
- 1.15× 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
- 6wrmleauhk
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 8.75 minutes | 10 min 6 s | 1.15× longer | |
| Four times | 140 minutes | 2 h 25 min | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 8.75 minutes | 8 min 31 s | Within 5% | |
| Gemini 4 Argon | 2.25 minutes | 2 min 51 s | 1.27× longer | |
| MiMo V2.6 Pro | 11.25 minutes | 15 min 25 s | 1.37× longer | |
| MiMo V2.6 Pro UltraSpeed | 10 minutes | 38 min 7 s | 3.81× longer | |
| Muse Wonder 1.0 | 9.5 minutes | 1 h 52 min | 11.77× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026