Benchmarks

A topic hub collecting every article tagged Benchmarks. Use it to explore related posts and follow this theme across the site.

6 articles

Explore More Topics

AI Agents AI Architecture LLM Claude Code AI Engineering

AI Agents Browser AI WebGPU WebLLM Mobile Benchmarks Frontend Chrome

On-Device AI on Phones: The 4 tok/s Reality

Phones can run LLMs in the browser — at 4–9 tok/s on flagships, with tab crashes, 76-second first tokens, and feature detection that lies. A mobile benchmark study with a warmup-gating pattern you can ship.

Sep 17, 2026 23 min read

Oh My Pi Coding Agents Developer Tools Agent Architecture Context Engineering Claude Code OpenCode Cursor Benchmarks

Oh My Pi (omp.sh): A Quick Look at the Hardened Coding Agent CLI

A deep-dive tour of Oh My Pi (omp.sh) — examining 'The Harness Problem', why edit tools swing model pass rates by up to 10×, built-in Hashline patching, AST refactoring, visual Snapcompact, and how it compares to OpenCode, Claude Code, and Cursor.

Aug 28, 2026 19 min read

AI LLM AI Engineering OpenAI Inference Benchmarks Open Source

How Fast Is gpt-oss-120b? Speed, Quality, and Routing Tradeoffs in 2026

For engineers evaluating gpt-oss-120b: OpenAI's open-weight model is fast for an open reasoning checkpoint, but throughput depends heavily on the provider and benchmark view. Here is how to read Artificial Analysis, OpenRouter trends, and the cost tradeoffs behind fast inference.

Jul 3, 2026 20 min read

RAG MCP Performance Benchmarks Open Source Cost Optimization AI Engineering

MCP + RAG Performance Stack: Tools, Benchmarks, and Decision Guide

A technical follow-up for engineers choosing embeddings, vector stores, rerankers, caches, and eval libraries for production MCP + RAG over public app data — with benchmark-backed comparisons and three reference stacks.

Jun 30, 2026 19 min read

AI Agents Prompt Engineering Coding Agents Benchmarks Developer Tools Product Management Loop Engineering

When Is a Prompt Enough, and When Do AI Agents Need More?

A research-backed guide for engineers and PMs on what is now redundant with stronger coding agents, when a good prompt is sufficient, and when prompts need scaffolding, tools, evals, and workflow design.

Jun 3, 2026 17 min read

AI Agents Claude Code Cursor Agent Skills Benchmarks Developer Tools Loop Engineering

Skills vs Default Agents: Do Coding Skills Really Improve Claude Code and Cursor?

A practical research audit for engineers and PMs: when agent skills improve coding agents, when default agents plus repo context are enough, and how to evaluate the tradeoff.

Jun 2, 2026 14 min read

Luis Mori Guerra

Recent Articles

Topics