OSWorld 2.1 (offline set, partial) leaderboard
As of November 14, 2026, among the results listed here, Anthropic Claude Fable 5.2 has the highest reported OSWorld 2.1 (offline set, partial) score, 89.3%, published by Anthropic, ahead of Anthropic Claude Fable 5.1 at 83.5%. 2 models have a OSWorld 2.1 (offline set, partial) result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
2 models ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 89.3% | Not published | Anthropic | November 9, 2026 (model release) |
| 2 | Claude Fable 5.1 | 83.5% | Not published | Anthropic | November 9, 2026 (model release) |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- All ranked results use the same reported setting.
- Spread
- 89.3% to 83.5% across 2 models.
- Freshness
- Published November 9, 2026.
What OSWorld 2.1 (offline set, partial) measures
OSWorld 2.1 (offline set, partial) appears in the release announcements of Anthropic. We have not found a public write-up of the benchmark itself yet.