skills.rest
BioInfo
BioInfoCOMMUNITY
Explore all skills by this author →
Website𝕏@bioinfoGitHub

artificial-analysis

Retrieve current LLM and media model benchmarks from artificialanalysis.ai.

1|Updated May 8, 2026
Search Tags:#pricing#model comparison#latency#llm benchmarking#tokens per second#elo ratings#api caching
One-click install
npx skills add https://github.com/BioInfo/rundatarun --skill artificial-analysis
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: artificial-analysis
Source: https://github.com/BioInfo/rundatarun/tree/main/skills/artificial-analysis
Command: npx skills add https://github.com/BioInfo/rundatarun --skill artificial-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of choosing between competing LLMs and media models when vendor marketing and outdated training-data recall don’t reflect current performance.

Core Features & Use Cases

  • Head-to-head model comparisons: Produces a short ranked set of 3–5 models for a given metric (coding, math, intelligence, speed/TTFT, or blended $/1M tokens).
  • Live benchmark sourcing with caching: Pulls results from artificialanalysis.ai and caches each endpoint for 1 hour to keep repeated queries fast.
  • Media model Elo lookups: Returns Elo ratings for text-to-image, image-editing, text-to-speech, text-to-video, and image-to-video leaderboards.
  • Use case: If you’re evaluating which model to integrate for coding, you can compare contenders on coding and speed and decide based on the specific tradeoffs and price.

Quick Start

Ask: "Compare Opus 4.7 and GPT-5.5 on coding and latency and tell me the cheapest option among the top 3 right now."

Frequently Asked Questions about artificial-analysis

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

FAQPage Schema
How do I compare LLM pricing and latency for multiple models?▼

Live LLM benchmark metrics are fetched from artificialanalysis.ai instead of relying on outdated training data, ensuring you get current pricing, latency, and performance data for accurate model comparisons.

How do I find the fastest or cheapest LLM for coding tasks right now?▼

You find the fastest or cheapest LLM by asking this Skill to compare candidates on coding, speed, or blended $/1M token metrics, which returns a ranked subset of models based on live benchmark data.

Can I get Elo ratings for text-to-image and text-to-video models?▼

An API key is required to retrieve benchmark data. The Skill also applies a 1-hour endpoint cache to keep repeated queries fast and avoid redundant external requests to artificialanalysis.ai.

Do I need an API key to benchmark models and check token speeds?▼

An API key is required to retrieve benchmark data. The Skill also applies a 1-hour endpoint cache to keep repeated queries fast and avoid redundant external requests to artificialanalysis.ai.

What are the limitations of using cached endpoint data for model comparisons?▼

Endpoint data is cached for 1 hour, meaning rapidly changing benchmark metrics may briefly appear outdated. The Skill returns a concise ranked subset rather than an exhaustive list of all available models.

Related Skills

Explore More Data & Analytics Skills→
nelohenriqnelohenriq
1

gif-search

Search and retrieve GIF URLs from the Tenor API using curl and jq.

Community
Basic
ConsiliencyConsiliency
8

model-discovery

Discover and classify AI model names from provider APIs.

Official
Intermediate
fjpulidopfjpulidop
9

telemetry

Analyze per-agent execution telemetry from CLAUDE CLI JSONL logs and metadata.

Community
Advanced
doanchienthangdevdoanchienthangdev
4

evaluation-methodology

Evaluate AI model outputs with exact match, semantic similarity, LLM-as-judge, and ELO ranking.

Community
Intermediate