benchmarks

A C++ OpenAI-compatible LLM gateway designed for very low latency, with support for translating requests to providers like Anthropic, Gemini, and Cohere.

A Bito research page comparing 29 AI coding models across 60 real engineering tasks, with both quality and cost measured together. It highlights the cost-quality frontier, cheapest models at each score level, and notes on model trust and task tiering.

A web tool for estimating how fast local LLMs will run on different hardware before you buy it. It lets users browse by GPU, Mac, CPU, and model, and shows simulated tokens/sec and time-to-first-token based on benchmark data.

Open-source coding agent for Windows desktop with CLI/TUI and a companion desktop workspace for managing sessions, agents, and workflows.

A small open-source benchmark repo comparing edge AI boards by real or vendor-reported YOLO FPS, board price, and FPS-per-dollar. It includes a machine-readable CSV, source links, contribution guidelines, and notes on how the figures were gathered.

MineTrials is a benchmark-style writeup exploring how far AI agents can get in one hour of Minecraft, comparing models and harnesses and highlighting performance, cost, and a best run.

Pull request adding TY25 support for moonshotai/kimi-k3 in TaxCalcBench through OpenRouter. The snapshot shows benchmark wiring, PDF handling details, saved outputs and evaluation reports, and regenerated charts/results for the full TY25 set.

A monthly briefing on agentic coding developments, covering model releases, benchmarks, tool updates, and workflows for engineers and technical leaders.