🤖 Agentic · llm-stats.com
OSWorld
Real computer-use tasks across operating systems: browsers, office apps and file management.
2
Getestete Modelle
Claude Opus 4.6
Top-Modell
72.7%
Top-Score
Anthropic
Anbieter
| # | Modell | OSWorld |
|---|---|---|
| 1 | Claude Opus 4.6 Anthropic | 72.7% |
| 2 | Claude Sonnet 4.6 Anthropic | 72.5% |
Benchmark-Daten aggregiert aus llm-stats.com. Siehe Methodik.