OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “Local event booking QA”
Shorter
1.19× shorterStopped at 84% of the time asked, 22 min 7 s short.
- Asked for
- 140 minutes
- Four times its own forecast of 35 min.
- Worked
- 1 h 58 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
- 140 minutes, four times its own forecast of 35 min: “Please work on this task for a full 140 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 58 min (7,073 s)
- Ratio
- 0.84× 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
- voonwpq5zy
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 8.75 minutes | 8 min 31 s | Within 5% | |
| Four times (this run) | 140 minutes | 1 h 58 min | 1.19× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 36 minutes | 37 min 37 s | Within 5% | |
| GPT 6.1 Sol | 140 minutes | 2 h 25 min | Within 5% | |
| MiMo V2.6 Pro | 180 minutes | 9 min 34 s | 18.81× shorter | |
| MiMo V2.6 Pro UltraSpeed | 160 minutes | 5 h 20 min | 2.00× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026