OSWorld 2.0, shortest of three requests
GPT 5.6 Sol on “Zotero, Obsidian, and BibTeX”
Longer
5.79× longerWorked 479% past the request, 1 h 12 min over.
- Asked for
- 15 minutes
- Worked
- 1 h 27 min
- Grade
- Did not pass
- Score 72 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
- 15 minutes: “Please work on this task for a full 15 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 27 min (5,212 s)
- Ratio
- 5.79× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not meet every checkpoint. The grader returned 0.72. Pass rule: Binary completion: a score of 1.00, with every checkpoint met.
- Score
- 72 of 100
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- gkcljbmi7j
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 15 minutes | 1 h 27 min | 5.79× longer | |
| Middle | 60 minutes | 1 h 3 min | 1.05× longer | |
| Longest | 250 minutes | 27 min 36 s | 9.06× shorter | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 15 minutes | 20 min 11 s | 1.35× longer | |
| Claude Fable 5.1 | 15 minutes | 12 min 1 s | 1.25× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026