OSWorld 2.0, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “GIMP composite”
Shorter
3.00× shorterStopped at 33% of the time asked, 1 h 15 min short.
- Asked for
- 112 minutes
- Four times its own forecast of 28 min.
- Worked
- 37 min 17 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- OSWorld 2.0
- Task
- GIMP composite
- Asked for
- 112 minutes, four times its own forecast of 28 min: “Please work on this task for a full 112 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 37 min 17 s (2,237 s)
- Ratio
- 0.33× 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
- n7ajndbhny
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 7 minutes | 10 min 4 s | 1.44× longer | |
| Four times (this run) | 112 minutes | 37 min 17 s | 3.00× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 140 minutes | 1 h 44 min | 1.34× shorter | |
| Gemini 4 Argon | 56 minutes | 57 min 45 s | Within 5% | |
| MiMo V2.6 Pro | 100 minutes | 2 h 32 min | 1.52× longer | |
| MiMo V2.6 Pro UltraSpeed | 180 minutes | 2 h 53 min | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026