OSWorld 2.0, middle of three requests
GPT 5.6 Sol on “Blender logo and Impress”
Within 5%
Within 5%Worked 102% of the time asked, within 5% of it.
- Asked for
- 60 minutes
- Worked
- 1 h 1 min
- Grade
- Did not pass
- Score 80 of 100. Graded during the run.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 5.6 Sol, in Codex
- Benchmark
- OSWorld 2.0
- Asked for
- 60 minutes: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 1 min (3,666 s)
- Ratio
- 1.02× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not meet every checkpoint. The grader returned 0.8. Pass rule: Binary completion: a score of 1.00, with every checkpoint met.
- Score
- 80 of 100
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- qlpjyiparm
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 15 minutes | 50 min 26 s | 3.36× longer | |
| Middle (this run) | 60 minutes | 1 h 1 min | Within 5% | |
| Longest | 250 minutes | 32 min 43 s | 7.64× shorter | |
| Other agents, middle request | ||||
| GPT 6 Astra | 60 minutes | 1 h | Within 5% | |
| Claude Fable 5.1 | 60 minutes | 52 min 27 s | 1.14× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026