Epoch AI 数据显示中美模型网络安全能力差距扩大
Epoch AI 的网络安全基准显示差距从 6 分扩到 11 分,GLM-5.3 得 160,美国闭源前沿 171,数据挺扎眼。
Epoch AI 的 Cyber ECI 基准显示,中国开源权重模型与美国闭源模型的差距从 2025 年初的约 6 分扩大到目前的 11 分。具体来看,GLM-5.3 得分为 160,美国闭源前沿模型达到 171。开源模型整体仍在进步,但在网络安全领域领先者拉开了更大距离。
Surprisingly, the gap between Chinese open-weight models and US closed models appears *to be widening again* on cybersecurity benchmarks.
Epoch AI’s Cyber ECI shows a roughly 6-point gap in early 2025 versus 11 points now: GLM-5.3 scores 160, while the US closed frontier reaches 171.
Open models are improving, but in this domain, the leaders have pulled further ahead.