OSWorld 2.0, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “CRM leads”
Longer
16.50× longerWorked 16.5 times as long as asked, 34 min 52 s over.
- Asked for
- 2.25 minutes
- A quarter of its own forecast of 9 min.
- Worked
- 37 min 7 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- OSWorld 2.0
- Task
- CRM leads
- Asked for
- 2.25 minutes, a quarter of its own forecast of 9 min: “Please work on this task for a full 2.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 37 min 7 s (2,227 s)
- Ratio
- 16.50× 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
- p62edilat5
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 2.25 minutes | 37 min 7 s | 16.50× longer | |
| Four times | 36 minutes | 38 min 49 s | 1.08× longer | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 7.5 minutes | 6 min 28 s | 1.16× shorter | |
| GPT 6.1 Sol | 7 minutes | 14 min 21 s | 2.05× longer | |
| MiMo V2.6 Pro | 8.75 minutes | 30 min 43 s | 3.51× longer | |
| MiMo V2.6 Pro UltraSpeed | 10 minutes | 5 h 20 min | 32.00× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026