DeepSeek V4 Pro Tops Security Benchmark with 87.5% Vulnerability Discovery Rate
solyarisoftware · x · 2026-08-13
In a recent cybersecurity benchmark, DeepSeek V4 Pro 0813 outperformed all other models in finding vulnerabilities. At pass@3, it rediscovered 87.5% of the benchmark CVEs, significantly beating Opus 5 and Qwen 3.8 at 81.3%.
However, this comes with tradeoffs: precision sits at only 65.6% (far below GPT-5.6-Sol's 86.4%). The model also shows unpredictability, finding an average of 58.3% of vulnerabilities per run, requiring combined runs for optimal results.
Related event: DeepSeek V4 Pro Released and Potentially Withdrawn Due to Wrong Version(18 posts)→
More from Models
- GLM 5.5 rumored to drop soon, coding ability expected to match frontier models — bindureddy · 2026-10-16
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16
- DIY benchmark ranks 18 models on subjective judgments, GLM-5.3 tops consensus match — arkuto · 2026-10-16
- Bindu Reddy: Google's Argon excels at complex doc writing at half the cost of Opus — bindureddy · 2026-10-16
- MAI-2 is 2x bigger than V4-Pro while V4.1F is 3x smaller: Microsoft's scaling ladder questioned — teortaxesTex · 2026-10-16
- Step 5 Preview hits DeepInfra day-zero: 600B MoE, 1M context, $1/M input tokens — StepFun_ai · 2026-10-16