artificial-analysis-compare — Claude Code skill: setup guide
artificial-analysis-compare compares LLM benchmark scores, pricing, and output speeds using the Artificial Analysis API.
no license 1 installs ★ 13 updated 2025-12-22
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a claude-codeWhat artificial-analysis-compare 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.
What it helps with
- 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 for the agent
- 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.
How to install artificial-analysis-compare
1Skills CLI (Vercel)
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a claude-code2Manually: put the files in place
~/.claude/skills/artificial-analysis-compare/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/artificial-analysis-compare/
1Skills CLI (Vercel)
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a codex2Manually: put the files in place
.agents/skills/artificial-analysis-compare/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a cursor2Manually: put the files in place
.cursor/skills/artificial-analysis-compare/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install alexfazio/artificial-analysis-compare artificial-analysis-compare2Manually: put the files in place
.github/skills/artificial-analysis-compare/SKILL.md1Skills CLI (Vercel)
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a gemini-cli2Platform CLI
gemini skills install https://github.com/alexfazio/artificial-analysis-compareManually: put the files in place
.devin/skills/artificial-analysis-compare/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about artificial-analysis-compare
How to install artificial-analysis-compare in Claude Code?
Run npx skills add alexfazio/artificial-analysis-compare --skill artificial-analysis-compare -a claude-code in your terminal.
What does artificial-analysis-compare do?
It pulls live data from the Artificial Analysis API to evaluate LLMs across benchmark metrics, response latency, and pricing.
Does artificial-analysis-compare require an API key?
Yes, it needs an Artificial Analysis API key. You can supply it via the AA_API_KEY environment variable or let the warmup script save it to .config/config.json.