OSWorld 2.1 (offline, OpenAI)Agent多模态

OpenAI's OSWorld 2.1 offline-set result. The release does not specify partial versus strict scoring or task count; kept separate from explicitly defined variants.

排行数据源

#模型得分

1

GPT-6 AstraOpenAI · max; offline set; partial/strict scoring not specified

80.9%

2

GPT-6.1 TerraOpenAI · max; offline set; partial/strict scoring not specified

74.2%

共 2 个模型

返回基准目录