# artificial-analysis-compare

artificial-analysis-compare compares LLM benchmark scores, pricing, and output speeds using the Artificial Analysis API.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 1 install · ★ 13 repo stars
- Author: alexfazio
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/alexfazio/artificial-analysis-compare/tree/HEAD/SKILL.md
- Updated: 2025-12-22
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/artificial-analysis-compare

## What it does

This skill queries Artificial Analysis to evaluate language models side by side. It pulls evaluation numbers for benchmarks like GPQA, LiveCodeBench, or AIME 2025, alongside input and output token rates. Before fetching endpoint data, it prompts for your target priorities, such as reasoning, coding benchmarks, or cost efficiency.

Every run begins with `scripts/warmup.py`, which detects `python3` or `uv` and checks for the `requests` package. The tool requires a valid Artificial Analysis API key stored in `.config/config.json` or exported as `AA_API_KEY`. Without this token, requests to the models endpoint will fail.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/artificial-analysis-compare/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/artificial-analysis-compare/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/artificial-analysis-compare/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/artificial-analysis-compare/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install alexfazio/artificial-analysis-compare artificial-analysis-compare
```

2. **Manually: put the files in place**
- File: `.github/skills/artificial-analysis-compare/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/alexfazio/artificial-analysis-compare
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/artificial-analysis-compare/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/alexfazio/artificial-analysis-compare/tree/HEAD/SKILL.md

## When to use it
- compare token pricing across different model providers
- find top-performing models on LiveCodeBench for coding tasks
- measure token generation speed alongside time to first token
- generate a ranked list of models filtered by cost and reasoning

## Example prompts
- Compare latency and pricing between Claude 3.5 Sonnet and GPT-4o.
- Which model scores highest on recent math benchmarks?
- Show a cost-performance table for top coding LLMs.

## Similar
- [ATOM Pricing Intelligence](https://affpapa.org/en/nevibecode/mcp/atom-pricing-intelligence.md) — MCP server · 4780 installs
- [huggingface-best](https://affpapa.org/en/nevibecode/skills/huggingface-best.md) — skill · 2000 installs
- [InferCPI](https://affpapa.org/en/nevibecode/mcp/infercpi.md) — MCP server
- [checkpoint-promotion](https://affpapa.org/en/nevibecode/skills/checkpoint-promotion.md) — skill · 2600 installs
- [mandela](https://affpapa.org/en/nevibecode/skills/mandela.md) — skill · 1500 installs
- [cli-eval](https://affpapa.org/en/nevibecode/skills/cli-eval.md) — skill · 1300 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
