News | STAC - Insight for the Algorithmic Enterprise

Posted August 6, 2025

LLM-Based RAG Evaluation Metrics: Model Relatedness and Consistency

Evaluating the Evaluators: How LLM Relatedness Impacts Scoring-Based Metrics in RAG Systems

Posted October 12, 2017

Max Actionable Latency of 98 nanoseconds with 68-byte frames at 1 Gbps ingress

Posted October 9, 2017

Lowest max latency ever reported at both the base rate and very high rates

Posted October 2, 2017

2.89x the speed of previous generation x86 solution in warm runs of baseline Greeks

Posted July 31, 2017

Highest throughput and efficiency for any publicly reported system to date

Posted July 10, 2017

Skylake-based servers set multiple records in STAC-M3 Shasta benchmarks

Posted June 25, 2017

32.7x the throughput of a larger Hadoop streaming cluster.

Posted May 8, 2017

Spark throughput was highest when managed by IBM Spectrum Conductor with Spark.

For the latest on research, events and related news please see stacresearch.com/news

This page is where you will find archived articles.