Artificial Analysis connector for AI agents

CALL ANY TOOL

6 tools for model benchmarks in Artificial Analysis: list language models with intelligence scores, prices, and speed, and read the text-to-image, image editing, text-to-video, image-to-video, and text-to-speech leaderboards.

artificialanalysis_get_image_editing_leaderboard

Get image editing leaderboard

Get the Artificial Analysis image editing leaderboard: Elo ratings for models that edit an existing image from an instruction, from the Artificial Analysis arena. Returns ranked models with id, name, slug, creator, Elo, rank, 95% confidence interval, arena appearances and release date. Only current models with at least 500 arena appearances are listed. Use this to compare image editing models. Use artificialanalysis_get_text_to_image_leaderboard for models that generate new images from a text prompt.

Parameters

Name

Type

Required

Description

—

No parameters required

artificialanalysis_get_image_to_video_leaderboard

Get image to video leaderboard

artificialanalysis_get_text_to_image_leaderboard

Get text to image leaderboard

artificialanalysis_get_text_to_speech_leaderboard

Get text to speech leaderboard

artificialanalysis_get_text_to_video_leaderboard

Get text to video leaderboard

artificialanalysis_list_llm_models

List llm models

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Artificial Analysis tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["artificialanalysis"], toolNames: [
    "artificialanalysis_list_llm_models",
    "artificialanalysis_get_text_to_image_leaderboard",
    "artificialanalysis_get_text_to_video_leaderboard"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Compare the top language, image, and video models by benchmark score" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["artificialanalysis"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Compare the top language, image, and video models by benchmark score" }],
  tools,
});

// Execute the tool call with the user's vaulted Artificial Analysis API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["artificialanalysis"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Compare the top language, image, and video models by benchmark score" }],
  tools,
});

// Tool call runs with the user's vaulted Artificial Analysis API key
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["artificialanalysis"] }, pageSize: 100,
});

const agent = new Agent({
  name: "model_research_agent",
  model: "gemini-2.5-pro",
  instruction: "Artificial Analysis tools scoped to this user",
  tools,
});

await agent.run("Compare the top language, image, and video models by benchmark score");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Artificial Analysis tool. Click to copy, paste into your agent, done.

Language models

Copy the prompt

Copied

Rank the language models by Artificial Analysis Intelligence Index.

Copy the prompt

Copied

Which models have the lowest blended price per million tokens?

Copy the prompt

Copied

Compare median time to first token across the top 5 models.

Image models

Copy the prompt

Copied

Show the top 5 text-to-image models by Elo.

Copy the prompt

Copied

Which image editing model ranks first in the arena?

Copy the prompt

Copied

List the text-to-image models with their 95% confidence intervals.

Video and speech

Copy the prompt

Copied

Show the top text-to-video models broken down by style category.

Copy the prompt

Copied

Which image-to-video model has the most arena appearances?

Copy the prompt

Copied

Rank the text-to-speech models by Elo.

SEE HOW AUTH WORKS

Each user connects their own Artificial Analysis API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

1

Authorize

Your user connects

Artificial Analysis

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Artificial Analysis

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Artificial Analysis

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Artificial Analysis

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other AI and analytics connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Test other agents

See the same per-user auth pattern across other AI and analytics connectors.

GTM

Competitive intelligence briefing agent

Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Artificial Analysis API key looks fine in a demo. In production every benchmark lookup looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Artificial Analysis today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Artificial Analysis as the user or through a shared API key?

As the user. Each user connects their own Artificial Analysis API key once, and Scalekit sends it with every call. Audit logs attribute every benchmark lookup to that user, not a shared service account.

Where is the Artificial Analysis API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Artificial Analysis?

Yes. Every Artificial Analysis tool is read-only: the agent can list benchmarks and leaderboards but cannot change anything. Filter by tool name in listScopedTools to expose only what you want, for example artificialanalysis_list_llm_models alone. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Artificial Analysis access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

What data do the leaderboards include?

The image and video leaderboards return ranked models with creator, Elo, rank, 95% confidence interval, arena appearances, and release date, limited to current models with enough arena appearances. artificialanalysis_list_llm_models returns intelligence, coding, and math indexes, price per million tokens, median output speed, and time to first token.

Artificial Analysis MCP server for AI agents

Tools your model research agent reaches for on Artificial Analysis, scoped per user.