Results for llm-benchmark

Core package for llm-benchmark CLI

LLM benchmark toolkit for pi coding agent. Probes every available model with real streaming API calls and ranks by latency, cost, and output quality. Provides curated model chain and blacklist for smart model selection in pi-recap and other extensions.

LLM Benchmark Transparent Proxy — intercept LLM API requests and collect token usage metrics

MCP server for the PipelineScore LLM benchmark — exposes run_benchmark / get_user_leaderboard / get_user_profile tools to any MCP-compatible client (Claude Code, Codex, Cursor, Continue, Cline). Lets your AI drive local-first LLM benchmarking on your hard

Strip comments from JSON. Lets you use comments in your JSON files!

Neo-Async is a drop-in replacement for Async, it almost fully covers its functionality and runs faster

Intl.LocaleMatcher ponyfill

Specialized fast async file writer

node-simple-lru-cache =====================

A fast alternative to legacy querystring module

High-performance Base64 encoder and decoder

Escape string for use in HTML

🔎 A simple, tiny and lightweight benchmarking library!

A node API for the dprint TypeScript and JavaScript code formatter

A simple MD5 hash function for JavaScript supports UTF-8 encoding.

The lightest signal library.

Functional tree editing, manipulation & navigation

Faster swc nodejs binding

Classify GPU's based on their benchmark score in order to provide an adaptive experience.

Fastest, most accurate & effecient user agent string parser, uses Browserscope's research for parsing

Fast, disk space efficient package manager

TypeScript definitions for benchmark

Fastest stable deterministic JSON.stringify()

Left pad a string with zeros or a specified string. Fastest implementation.