Event ·Multi-source

Astra模型在DeepsecBench成为最佳网络安全模型

Astra模型在@vercel DeepsecBench基准测试中表现最佳。该模型完成测试仅需49分钟，而Sol模型需要约4小时，且得分更高，成本相近。与Claude Opus 5 max相比，Astra效率更高且价格便宜50%。

Current read

Astra在网络安全基准测试中超越Sol和Claude Opus 5 max，速度提升5倍，成本降低一半。

11 sources73° AI heatLast updated 2026/9/5 17:11:16

Evidence

11 sources

Primary sourceGuillermo Rauch

2026/9/5 17:11:16View source

Related source 1orange.ai

2026/9/3 23:36:56View source

Related source 2歸藏(guizang.ai)

2026/9/4 00:59:38View source

Related source 3向阳乔木

2026/9/4 08:57:07View source

Related source 4Decoder

2026/9/4 17:23:35View source

Related source 5Simon Willison’s Weblog

2026/9/3 20:18:41View source

Related source 6lmarena.ai

2026/9/3 20:26:06View source

Related source 7Perplexity

2026/9/3 21:10:17View source

Related source 8Aravind Srinivas

2026/9/3 21:13:22View source

Related source 9Gary Marcus

2026/9/4 01:34:52View source

Related source 10Browser Use

2026/9/6 04:17:41View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story