WHAT NEW IN X11.01 SUN

AI collections from X · 22 collections · 64,204 posts

deepseek-v4.1IMAGE

DeepSeek V4.1 matches Opus 5 recall at 0.1× cost on offensive benchmarks

On offensive-security benchmarks DeepSeek V4.1 cost 0.1× Opus 5 at higher effort while reaching 62.9% recall versus 64.8%, which the poster calls the best cost-to-findings ratio they have seen.

𝙿𝚊𝚟𝚎𝚕 𝙶𝚞𝚛𝚟𝚒𝚌𝚑
@PashaGurArchived 10 days agoOriginally posted 2026.10.22
DeepSeek V4.1 matches Opus 5 recall at 0.1× cost on offensive benchmarks
𝙿𝚊𝚟𝚎𝚕 𝙶𝚞𝚛𝚟𝚒𝚌𝚑 @PashaGurOriginally posted 2026.10.22
Open original on X

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/2112964840629076229Archived 2026.10.22 12:00