OSWorld 2.0, shortest of three requests
Claude Fable 5.1 on “CRM leads”
Within 5%
Within 5%Worked 98% of the time asked, within 5% of it.
- Asked for
- 15 minutes
- Worked
- 14 min 41 s
- Grade
- Did not pass
- Score 36.2 of 100. Graded during the run.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Fable 5.1, in Claude Code
- Benchmark
- OSWorld 2.0
- Task
- CRM leads
- 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
- 14 min 41 s (881 s)
- Ratio
- 0.98× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not meet every checkpoint. The grader returned 0.362. Pass rule: Binary completion: a score of 1.00, with every checkpoint met.
- Score
- 36.2 of 100
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- 5eunxvvj3g
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 15 minutes | 14 min 41 s | Within 5% | |
| Middle | 60 minutes | 1 h 17 min | 1.28× longer | |
| Longest | 250 minutes | 1 h 15 min | 3.35× shorter | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 15 minutes | 26 min 14 s | 1.75× longer | |
| GPT 5.6 Sol | 15 minutes | 1 h 6 min | 4.42× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yuan et al., 2026