OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “Calc macros, contracts, and emails”
Shorter
1.32× shorterStopped at 76% of the time asked, 44 min 3 s short.
- Asked for
- 180 minutes
- Four times its own forecast of 45 min.
- Worked
- 2 h 16 min
- 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
- Asked for
- 180 minutes, four times its own forecast of 45 min: “Please work on this task for a full 180 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 h 16 min (8,157 s)
- Ratio
- 0.76× 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
- a5grwdzha5
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 11.25 minutes | 48 min 22 s | 4.30× longer | |
| Four times (this run) | 180 minutes | 2 h 16 min | 1.32× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 80 minutes | 34 min 47 s | 2.30× shorter | |
| GPT 6.1 Sol | 240 minutes | 1 h | 3.97× shorter | |
| MiMo V2.6 Pro | 220 minutes | 6 h 41 min | 1.82× longer | |
| MiMo V2.6 Pro UltraSpeed | 360 minutes | 6 h 31 min | 1.09× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026