模型58
GPT-6.2 Astra 在 Terminal-Bench Science 0.1 上超过 GPT-6 Astra
原标题:GPT-6.2 Astra sets a new high on Terminal-Bench Science 0.1, which tests how well models carry out scientific work in a terminal, scoring...
OpenAI Developers 称 GPT-6.2 Astra 在 Terminal-Bench Science 0.1 上创下新高,该基准测试模型在终端中执行科研工作的能力。其得分比 GPT-6 Astra 高 9 个百分点,成本不到后者的 1/3。
中文译文尚未完成,先为你展示原文。
GPT-6.2 Astra sets a new high on Terminal-Bench Science 0.1, which tests how well models carry out scientific work in a terminal, scoring 9 percentage points higher than GPT-6 Astra at less than 1/3 the cost.
