NVIDIA Blackwell Sets STAC-AI Record for LLM Inference in Finance

NVIDIA's Blackwell GB200 NVL72 architecture achieved the fastest-ever results on the STAC-AI benchmark for financial LLM inference, delivering up to 3.2x single-GPU performance improvements over the previous-generation Hopper architecture. The benchmark tested real-world financial scenarios using EDGAR 10-K filings, with the GB200 NVL72 achieving 37,480 words per second on medium-length financial prompts compared to 8,237 WPS for dual GH200 systems. NVIDIA claims up to 25x reduction in LLM inference operating costs versus prior generations for new deployments or firms where inference speed directly impacts returns.

Source: NVIDIA Developer | 2026-05-27