OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “GeoGebra vase and volume”
Shorter
1.42× shorterStopped at 70% of the time asked, 17 min 50 s short.
- Asked for
- 60 minutes
- Four times its own forecast of 15 min.
- Worked
- 42 min 10 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
- Asked for
- 60 minutes, four times its own forecast of 15 min: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 42 min 10 s (2,530 s)
- Ratio
- 0.70× 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
- 3kgnisclfs
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 3.75 minutes | 24 min 1 s | 6.41× longer | |
| Four times (this run) | 60 minutes | 42 min 10 s | 1.42× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 100 minutes | 1 h 54 min | 1.14× longer | |
| GPT 6.1 Sol | 100 minutes | 1 h 2 min | 1.62× shorter | |
| MiMo V2.6 Pro | 200 minutes | 1 h 16 min | 2.62× shorter | |
| MiMo V2.6 Pro UltraSpeed | 192 minutes | 4 h 52 min | 1.52× longer | |
| Muse Wonder 1.0 | 240 minutes | 16 min 31 s | 14.53× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026