WHAT NEW IN X10.28 WED

AI collections from X · 22 collections · 58,925 posts

benchmarkIMAGE

DeepSeek V4.1 Flash trails only GPT-6 Astra on a cybersecurity CVE benchmark

On the author's CVE-rediscovery benchmark, DeepSeek V4.1 Flash hits 87.5% pass@3, behind only GPT-6 Astra at 90.6%, matches Opus 5 on single-run recall, and costs $2.40 per CVE found — 56x cheaper than Astra.

pilvar (Philippe Dourassov)
@pilvar222Archived 5 days agoOriginally posted 2026.10.22
DeepSeek V4.1 Flash trails only GPT-6 Astra on a cybersecurity CVE benchmark
pilvar (Philippe Dourassov) @pilvar222Originally posted 2026.10.22
Open original on X

Unsurprisingly, DeepSeek V4.1 Flash 1017 is mogging all other models on our cybersecurity benchmark - At pass@3, it rediscovered 87.5% of the benchmark CVEs (28/32). That ties DeepSeek V4 Pro 0813 for 2nd place, behind only GPT-6 Astra (90.6%) - Single-run recall is 70.8%, matching Opus 5 and Grok 4.7. The previous Flash was at 65.6% - Precision went from 78.9% to 86.4%, so most false positives are now gone Cost: $2.40 per CVE found. That’s 27x cheaper than Opus 5 ($64.96) and 56x cheaper than Astra ($135.23) @deepseek_ai keeps pushing the Pareto frontier 1/4 🧵

x.com/pilvar222/status/2113260594547524087Archived 2026.10.23 10:07