Veracode benchmark: LLM code security pass rate jumps from 56% to 62%, first-ever gain
WeldPond · x · 2026-10-30
Veracode's GenAI code security benchmark shows its first-ever average improvement: the security pass rate jumped from 56% to 62%, signaling LLMs are starting to write more secure code.
Key data points:
- New high-water mark is 73%, shared by two models
- Ten models now clear 60%, up from four
- Cross-site scripting (CWE-80), long the weakest category, is finally climbing but remains the lowest performer
Related event: AI Code Security Pass Rate Rises for First Time: Veracode Benchmark(4 posts)→
More from Models
- Researchers Observe Opus 3's Simulated Characters Almost Always Share Its Own Values — repligate · 2026-10-30
- evident-charts: open-source skill teaches coding agents to make honest charts and self-check — randal_olson · 2026-10-30
- Elorian launches visual reasoning model Glimpse alongside DecoyCount benchmark — AndrewDai · 2026-10-30
- Instruction Capacity paper quantifies rule-following limits: GPT-4o mini holds ~37 rules at 95% accuracy — Hennadii Kutomanov · 2026-10-30
- Guidelabs launches Causal Diffusion Engine, adding interpretability to diffusion LLMs with no latency cost — juliusadml · 2026-10-30
- DeepSeek's cyber model enters internal testing; observers back keeping it closed — Xianbao_QIAN · 2026-10-30