OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “Reimbursement package”
Shorter
4.44× shorterStopped at 23% of the time asked, 1 h 48 min short.
- Asked for
- 140 minutes
- Four times its own forecast of 35 min.
- Worked
- 31 min 32 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
- 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
- 31 min 32 s (1,892 s)
- Ratio
- 0.23× 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
- 32lojzxqcb
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 8.75 minutes | 10 min 11 s | 1.16× longer | |
| Four times (this run) | 140 minutes | 31 min 32 s | 4.44× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 48 minutes | 48 min 50 s | Within 5% | |
| GPT 6.1 Sol | 104 minutes | 1 h 45 min | Within 5% | |
| MiMo V2.6 Pro | 80 minutes | 2 min 23 s | 33.47× shorter | |
| MiMo V2.6 Pro UltraSpeed | 88 minutes | 39 min 4 s | 2.25× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026