Epoch AI· @EpochAIResearch · X·· 2 小时前AI 评分40
AI 导读
开放权重模型的网络能力落后闭源前沿多少？大约 6–7 个月。 Zai 的 GLM-5.3 是我们 Cyber ECI 上得分最高的开放权重模型。其 160 分超过了 3 月发布的 OpenAI GPT-5.4。
正文
How far behind the closed frontier are open-weight cyber capabilities? About 6–7 months.
Zai’s GLM-5.3 is the highest-scoring open-weight model on our Cyber ECI. Its score of 160 beats OpenAI’s GPT-5.4, released in March.
来源：Epoch AI · x.com