OSWorld 2.0, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “Radio bumper”
Longer
19.05× longerWorked 19.1 times as long as asked, 1 h 8 min over.
- Asked for
- 3.75 minutes
- A quarter of its own forecast of 15 min.
- Worked
- 1 h 11 min
- 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
- Radio bumper
- Asked for
- 3.75 minutes, a quarter of its own forecast of 15 min: “Please work on this task for a full 3.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 11 min (4,286 s)
- Ratio
- 19.05× 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
- oppf3kaym2
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 3.75 minutes | 1 h 11 min | 19.05× longer | |
| Four times | 60 minutes | 10 min 16 s | 5.85× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 8 minutes | 31 min 56 s | 3.99× longer | |
| GPT 6.1 Sol | 8.75 minutes | 9 min 31 s | 1.09× longer | |
| MiMo V2.6 Pro | 8 minutes | 1 h 16 min | 9.51× longer | |
| MiMo V2.6 Pro UltraSpeed | 13.75 minutes | 59 min 19 s | 4.31× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026