agentic Agentic · llm-stats.com

OSWorld

Real computer-use tasks across operating systems: browsers, office apps and file management.

3
Getestete Modelle
Claude Opus 4.6
Top-Modell
72.7%
Top-Score
Anthropic
Anbieter
#ModellOSWorldAnbieterPodium Score
1
72.7%
Anthropic61.2
2
72.6%
OpenAI86.2
3
72.5%
Anthropic38.1
Benchmark-Daten aggregiert aus llm-stats.com. Siehe Methodik.
0 / 4