Get started

Artificial Analysis for AI agents

Artificial Analysis publishes independent benchmarks comparing AI models and API providers on intelligence, cost, latency, and throughput, used by engineering teams to decide which model to build with. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Artificial AnalysisSee the 12 actions ↓
Developer toolsAPI keyMCP + RESTartificialanalysis.ai
AUDIT LOG · ARTIFICIAL ANALYSISPOLICY: acme-support
09:41:07 · claude · u_8f2read
artificial_analysis.list_language_models
List Language Models (Intelligence & Pricing)✓ allowed · 212ms
09:41:08 · claude · u_8f2read
artificial_analysis.list_image_editing_models
List Image-Editing Models (Arena)✓ allowed · 164ms
EVERY ARTIFICIAL ANALYSIS CALL, ON THE RECORD
01 · USE CASES

What agents do in Artificial Analysis.

01

Compare language model pricing and intelligence

List language models side by side with their intelligence index and pricing.

02

Check text-to-image arena rankings

List text-to-image models ranked by arena performance before choosing one to use.

03

Look up speech-to-text accuracy

List speech-to-text models ranked by word error rate for a side-by-side comparison.

02 · ACTIONS

12 Artificial Analysis actions, graded by risk.

Every Artificial Analysis action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

12

Look things up. Allowed by default.

  • artificial_analysis.list_language_models
    List Language Models (Intelligence & Pricing)
  • artificial_analysis.list_image_editing_models
    List Image-Editing Models (Arena)
  • artificial_analysis.list_text_to_image_models
    List Text-to-Image Models (Arena)
  • artificial_analysis.list_text_to_video_models
    List Text-to-Video Models (Arena)
  • artificial_analysis.list_image_to_video_models
    List Image-to-Video Models (Arena)
  • artificial_analysis.list_speech_to_text_models
    List Speech-to-Text Models (WER)
  • artificial_analysis.list_text_to_speech_models
    List Text-to-Speech Models (Arena)
  • artificial_analysis.list_speech_to_speech_models
    List Speech-to-Speech Models
  • artificial_analysis.list_music_with_vocals_models
    List Music-with-Vocals Models (Arena)
  • artificial_analysis.list_music_instrumental_models
    List Instrumental Music Models (Arena)
  • artificial_analysis.list_text_to_video_audio_models
    List Text-to-Video-with-Audio Models (Arena)
  • artificial_analysis.list_image_to_video_audio_models
    List Image-to-Video-with-Audio Models (Arena)

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Artificial Analysis in three steps.

  1. 01Your users connect Artificial AnalysisThey add their Artificial Analysis api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Artificial Analysis through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('artificial_analysis', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Artificial Analysis connects.

Users add their Artificial Analysis api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Artificial Analysis connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Artificial Analysis from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More developer tools apps.

GitHub896 actionsSupabase129 actions0CodeKit8 actionsAbly25 actionsAbstract3 actionsAddressfinder17 actionsAddresszen2 actionsAlchemy36 actions
ALL DEVELOPER TOOLS APPS →
07 · FAQ

Artificial Analysis and Arc0, answered.

Q01

Can I use Artificial Analysis with Claude, ChatGPT or Cursor?

Yes. Connect Artificial Analysis to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Artificial Analysis actions you allow.

Q02

How do users connect Artificial Analysis?

Users add their Artificial Analysis api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Artificial Analysis actions can my agent take?

12 in total: 12 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Artificial Analysis?

Yes. Allow read actions and deny writes in the Artificial Analysis policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Artificial Analysis too?

Yes. The same Artificial Analysis connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Artificial Analysis into your agent.

Your users connect Artificial Analysis once, under your brand. Your agent gets 12 actions behind your policies, with every call on the record.

Connect Artificial AnalysisBrowse all apps →

Free to build · MCP + REST · Audit log on every plan