Artificial Analysis Compare — AI skill for Claude Code
LLM model comparison skill using Artificial Analysis API - benchmarks, pricing, and performance metrics.
How to install Artificial Analysis Compare
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open alexfazio/artificial-analysis-compare and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Artificial Analysis Compare does
LLM model comparison skill using Artificial Analysis API - benchmarks, pricing, and performance metrics.
Alternatives in AI
- Codex — openai-codex Adversarial code review, Codex CLI integration, cross-model analysis 9.6k ★
- Ccstatusline — by sirmalloc - A highly customizable status line formatter for Claude Code CLI that displays model info, git b 5.5k ★
- Deepreasoning — A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthr 5.4k ★
README
artificial-analysis-compare
Compare LLM models using the [Artificial Analysis](https://artificialanalysis.ai) API. Get benchmark scores, pricing, and speed metrics across models like GPT-5, Claude, Gemini, and more.
API Key Required
You'll need an Artificial Analysis API key. Get one free at [artificialanalysis.ai/insights](https://artificialanalysis.ai/insights).
When you first invoke the skill, it'll ask for your key if one isn't configured.
**Heads up:** The key gets stored locally inside the skill directory (`.config/config.json`) so you don't have to enter it every time. Keep this in mind if you're sharing your skill folder.
What It Does
- Compares models by intelligence, coding, math, cost, or speed
- Multiple output formats (tables, detailed reports, rankings)
- Sources everything back to artificialanalysis.ai for verification
Related Skills
Artificial Analysis Skill
Agent skill that picks the right AI model using live benchmarks from artificialanalysis.ai. Works with Claude
Refresh Coder Comparison
Re-research the coder capability matrix — re-check benchmark boards, pricing, model rosters, safety evaluation
Rates
Show per-model pricing from real usage. Flags: --period [weekly monthly all] --compare (what-if cross-agent co
Earnings Model
Build earnings model with consensus comparison and scenario analysis
Moodtrip Hotel Search
Hotel search, comparison, reviews, pricing, and booking handoff via MoodTrip.ai MCP server. 12 tools including
Multi LLM
Parallel multi-LLM analysis — spawn Codex + Kimi + Gemini CLIs, compare with Claude
Related Agents
Jensen Huang Board
Use this agent for strategic board-level reviews, competitive analysis, ecosystem/platform thinking, data moat
Provider Tester
Use this agent when you need to test, debug, or validate LLM provider configurations. This includes verifying
Evolve Behavior Compare
Behavior comparison agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on refactor