deepseek-v4.1IMAGE

攻防基准：V4.1 以 0.1× Opus 5 成本达到 62.9% vs 64.8% 召回

攻防测试中 DeepSeek V4.1 成本仅为 Opus 5（更高 effort）的 0.1 倍，召回率 62.9% 对 64.8%，作者称是性价比最高的结果。

𝙿𝚊𝚟𝚎𝚕 𝙶𝚞𝚛𝚟𝚒𝚌𝚑

@PashaGur10 天前收录原推发布于 2026.10.22

攻防基准：V4.1 以 0.1× Opus 5 成本达到 62.9% vs 64.8% 召回

𝙿𝚊𝚟𝚎𝚕 𝙶𝚞𝚛𝚟𝚒𝚌𝚑 @PashaGur原推发布于 2026.10.22

DeepSeek V4.1 just got the best cost-to-findings ratio we've seen in our offensive benchmarks. 0.1× the cost of Opus 5 (higher effort) while matching almost the same recall (62.9% vs 64.8%). Opus 5 dropped 89 days ago. The gap is 3 months.

x.com/pashagur/status/2112964840629076229采集于 2026.10.22 12:00