PlanetScaleLangChainH2O.aiJane StreetCoreweaveShopifyHugging FaceAI Engineer+26

PlanetScaleBlog4d

TIN v1.0.6: 2-3x faster, with support for stemming

LangChainYouTube5d

Building Engine v2: How LangChain approaches agent improvement

H2O.aiBlog5d

H2O-Lightning-4B: #1 on JevBench, and Ahead of Jev Itself

Jane StreetBlog1w

Scaling and benchmarking a critical message bus using a new indexing strategy

CoreweaveBlog1w

How We Benchmark ARIA—and Why It Runs on Weave

ShopifyBlog1w

ShopGym: Realistic, reproducible sandboxes for shopping agents (2026)

Hugging FaceBlog2w

Beyond LoRA: Can you beat the most popular fine-tuning technique?

AI EngineerYouTube3w

Are LLM Performance Benchmarks Reliable? — Ashok Chandrasekar & Jason Kramberger, Google

NVIDIABlog3w

Benchmarking LLM Inference at Scale with AIPerf

PineconeBlog3w

VQ-bench: a Composable Vector Quantization Framework

AppleBlog3w

REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff

PlanetScaleBlog3w

Introducing TIN: full-text search for Postgres

DecagonBlog4w

DuetBench-2: Measuring agent self-improvement in production

Hugging FaceBlog7 Sept

MTEB: Massive Text Embedding Benchmark

QdrantBlog1 Sept

Enough with the Bad Benchmarks: Tools for Production-Grade Research

Hugging FaceBlog27 Aug

The Agent Said It Was Done. The Database Disagreed.

NVIDIABlog19 Aug

Evaluating AI Agent Skill Performance with NVIDIA SkillEvaluator

WeaviateBlog11 Aug

Scaling Test-Time Compute in Search Mode

CoreweaveBlog30 Jul

CoreWeave Leads MLPerf 0.7 Endpoints

PineconeBlog16 Jul

Behind the Benchmarking Pipeline

Showing the newest 43 of 86 posts.