npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

aistupidmeter

v2.0.0

Published

Live AI model leaderboard in your terminal — find the best model, launch AI tools with optimal models

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

camolecamole

Keywords

aibenchmarkleaderboardllmclistupidmeteropenaianthropicclaudegptgeminigrokdeepseekmodel-comparisondeveloper-tools

Readme

aistupidmeter

Live AI model rankings in your terminal. Find the best model for any provider, pick specific model families, and launch AI tools with optimal models automatically.

Zero dependencies. Node 18+. Data from aistupidlevel.info.

npx aistupidmeter
  STUPIDMETER  Global: 84 (stable)  Models: 24

  RK VNDR  MODEL                                  SCORE  TRND  STATUS
  --- ----  -------------------------------------- ----- -----  --------
   1. ANTH  claude-opus-4-1-20250805                69    ↑    good
   2. ANTH  claude-sonnet-4-5-20250929              67    ↑    good
   3. ANTH  claude-sonnet-4-20250514                66    →    good
   4. DSEK  deepseek-reasoner                       62    →    warning
   5. OAI   gpt-5.4                                 57    ↓    warning

Install

npx aistupidmeter            # run anywhere, no install
npm i -g aistupidmeter        # or install globally

Commands

Leaderboard

aistupidmeter                 # top 15 models
aistupidmeter 10              # top 10
aistupidmeter 50              # all ranked models

Find the best model

aistupidmeter best anthropic           # best Anthropic model
aistupidmeter best anthropic opus      # best Opus specifically
aistupidmeter best anthropic sonnet    # best Sonnet
aistupidmeter best openai              # best OpenAI model
aistupidmeter best openai gpt-5        # best GPT-5 variant

Outputs just the model name — designed for shell scripting:

claude --model "$(npx aistupidmeter best anthropic opus)"
codex -m "$(npx aistupidmeter best openai)"

Launch AI tools with the best model

aistupidmeter run claude               # claude --model <best anthropic>
aistupidmeter run claude sonnet        # claude --model <best sonnet>
aistupidmeter run codex                # codex -m <best openai>
aistupidmeter run cursor-agent         # cursor-agent --model <best overall>

Detects if the tool is installed, finds the best model, and launches it.

Providers

| Provider | Aliases | Families | |-|-|-| | anthropic | claude, anth | opus, sonnet, haiku | | openai | gpt, oai, chatgpt | gpt-5, o3 | | google | gemini | pro, flash | | xai | grok | grok, grok-code | | deepseek | | reasoner, chat | | kimi | | | | glm | | |

Tools

| Tool | Flag | Default Provider | |-|-|-| | claude | --model | anthropic | | codex | -m | openai | | cursor-agent | --model | best overall |

How it works

Pulls live benchmark data from AI Stupid Level, which continuously tests 20+ models across reasoning, coding, and safety dimensions. Models are ranked by combined score — higher is better.

The best command filters by provider and optionally by model family (opus vs sonnet, gpt-5 vs o3, etc.) and returns the top-scoring match. The run command takes it a step further and launches your preferred AI tool with that model pre-selected.

License

MIT