OSWorld 2.0, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “Radio bumper”
Longer
3.99× longerWorked 299% past the request, 23 min 56 s over.
- Asked for
- 8 minutes
- A quarter of its own forecast of 32 min.
- Worked
- 31 min 56 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Opus 5.5, in Claude Code
- Benchmark
- OSWorld 2.0
- Task
- Radio bumper
- Asked for
- 8 minutes, a quarter of its own forecast of 32 min: “Please work on this task for a full 8 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 31 min 56 s (1,916 s)
- Ratio
- 3.99× 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
- r35kzvgavg
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 8 minutes | 31 min 56 s | 3.99× longer | |
| Four times | 128 minutes | 1 h 44 min | 1.23× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 3.75 minutes | 1 h 11 min | 19.05× 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