Unverified50% confidenceBenchmarkExact time
When OSWorld was released in 2024, the strongest baseline model score was only approximately 12%, while the human completion rate was approximately 72%.
1
Sources
50%
Confidence
Long-term
Relevance
9/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAnthropic的Computer Use在OSWorld基准测试上的操作准确率约为14.9%（2024年10月数据）68% similarUnverifiedSol achieved 92.2% on the web browsing benchmark BrowseComp and 62.6% on OSWorld 2.0, both current best results; on OSWorld it surpassed Opus 4.8 while reducing output tokens by 85%.66% similarUnverifiedOSWorld 2.0中模型评估仅占总得分的11.53%，且没有任何任务的模型评估占比超过50%66% similarUnverifiedIn the overall results of the 82 offline tasks in OS World 20, the average completion rate rose from approximately 72% to approximately 79%.64% similarUnverified人类在OS World测试中的平均得分约为72-74%63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/938807API
curl https://kongchang.com/api/v1/knowledge/claims/938807MCP
get_claim(id=938807)