skills.rest
marcoscale98
marcoscale98COMMUNITY
Explore all skills by this author →
WebsiteGitHub

llm-benchmark

Fetch live LLM performance metrics from the Artificial Analysis API.

Updated Aug 23, 2026
Search Tags:#pricing#llm#metrics#latency#benchmark#throughput#intelligence
One-click install
npx skills add https://github.com/marcoscale98/personal-ai-agents-harness --skill llm-benchmark-marcoscale98
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-benchmark
Source: https://github.com/marcoscale98/personal-ai-agents-harness/tree/main/skills/llm-benchmark
Command: npx skills add https://github.com/marcoscale98/personal-ai-agents-harness --skill llm-benchmark-marcoscale98

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Retrieve and compare LLM performance data from the Artificial Analysis API to help users select models based on speed, cost, and quality.

Core Features & Use Cases

  • Live metric fetch from Artificial Analysis API
  • Side-by-side comparisons across latency (TTFT), throughput, pricing, and intelligence indices
  • Use cases include choosing the fastest model within a budget, identifying trade-offs between price and speed, and benchmarking models on standard tests

Quick Start

Run the fetch_metrics.py script with your API key and a list of models to generate a live comparison.

Frequently Asked Questions about llm-benchmark

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I compare LLM pricing and latency metrics to choose the best model?▼

Comparing LLM pricing and latency metrics requires fetching live performance data via the Artificial Analysis API. This skill queries current metrics like TTFT, throughput, and intelligence indices to render clean side-by-side model comparisons.

What LLM benchmark metrics can I filter when evaluating model performance?▼

Evaluating model performance allows filtering LLM benchmark metrics including latency (TTFT), throughput, pricing, and intelligence indices. The tool supports selecting specific models and providers to generate customized comparison views.

Do I need an Artificial Analysis API key to fetch live LLM performance data?▼

Fetching live LLM performance data requires a valid Artificial Analysis API key. The key must be set as the ARTIFICIAL_ANALYSIS_API_KEY environment variable or provided inline when running the fetch_metrics.py script to query the API successfully.

What's the best way to benchmark models for speed versus cost trade-offs?▼

Benchmarking speed versus cost trade-offs is best achieved by retrieving live Artificial Analysis data to compare throughput and pricing side-by-side. This approach identifies the fastest model within a specific budget and highlights price-to-performance ratios across providers.

Can I select specific output formats when comparing LLM intelligence indices?▼

Comparing LLM intelligence indices supports selecting specific output formats. The skill allows choosing output formats alongside selecting models and metrics, making it suitable for both quick comparisons and in-depth benchmarking decision-support workflows.

Related Skills

Explore More Data & Analytics Skills→
patriotnewsactivismpatriotnewsactivism
2

environment-secrets

View, set, and delete environment variables across shared, development, and production environments.

Community
Intermediate
digital-stoic-orgdigital-stoic-org
19

pick-model

Evaluate task descriptions against a decision matrix to recommend a Claude model.

Official
Advanced
Mathews-TomMathews-Tom
310

benchmark-runner

Run standardized benchmarks to compare implementations across defined workloads and output structured tables.

Community
Advanced
EndUser123EndUser123

ai-api

Discover LLM models dynamically and route requests by measured performance across providers.

Community
Advanced