# Classements LLM (LMArena, Epoch AI) (`rosmax/llm-leaderboards`) Actor

Collecte les classements de modèles de langage depuis LMArena et Epoch AI. Détecte les changements de rang, de rating, les nouvelles entrées et les sorties. Attribution CC BY obligatoire.

- **URL**: https://apify.com/rosmax/llm-leaderboards.md
- **Developed by:** [Maxime Rosito](https://apify.com/rosmax) (community)
- **Categories:** AI, Developer tools
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.80 / 1,000 enregistrements

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Classements LLM (LMArena)

### Description

Cet acteur collecte les classements de modèles de langage depuis le dataset LMArena hébergé sur Hugging Face.

**Source** : Dataset HF `lmarena-ai/leaderboard-dataset` (licence CC BY 4.0)

### Attribution obligatoire

Les données proviennent de LMArena et sont sous licence **CC BY 4.0**. Toute utilisation doit inclure l'attribution :

> "Source: LMArena Leaderboard Dataset (CC BY 4.0)"

Chaque item inclut automatiquement les champs `attribution` et `source_url`.

### Différenciation : historique et détection des changements

- **Conserve l'historique** entre les runs pour détecter les évolutions
- **Détecte automatiquement** : changements de rang (↑↓), changements de rating, nouvelles entrées, sorties du classement, nouvelles dates de publication
- **Modes** : `snapshot` (classement complet) | `changes` (deltas uniquement)

### Exemples

#### Input (mode snapshot)

```json
{
  "mode": "snapshot",
  "sources": ["lmarena"],
  "categories": ["text", "vision"],
  "maxItems": 100,
  "historyStoreName": "llm-leaderboards-history"
}
```

#### Output (snapshot)

```json
{
  "record_type": "snapshot",
  "source": "lmarena",
  "observed_at": "2026-09-25T06:00:00.000Z",
  "entry_key": "lmarena:text:gpt-4",
  "model_name": "gpt-4",
  "organization": "OpenAI",
  "category": "text",
  "rating": 1250.5,
  "rating_lower": 1245.2,
  "rating_upper": 1255.8,
  "rank": 1,
  "vote_count": 12543,
  "leaderboard_publish_date": "2026-09-24",
  "attribution": "LMArena Leaderboard Dataset (CC BY 4.0)",
  "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset"
}
```

#### Output (change détecté)

```json
{
  "record_type": "change",
  "source": "lmarena",
  "observed_at": "2026-09-25T12:00:00.000Z",
  "previous_observed_at": "2026-09-25T06:00:00.000Z",
  "change_type": "rank_up,rating_change",
  "diff_type": "changed",
  "model_name": "claude-3-opus",
  "rank": 2,
  "rating": 1248.3,
  "changes": [
    {
      "field": "rank",
      "old": 3,
      "new": 2,
      "delta_abs": -1
    },
    {
      "field": "rating",
      "old": 1245.1,
      "new": 1248.3,
      "delta_abs": 3.2,
      "delta_pct": 0.26
    }
  ]
}
```

### Catégories LMArena disponibles

- `text` : Modèles texte généraux (défaut)
- `text_style_control` : Contrôle de style
- `vision` : Modèles multimodaux
- `webdev` : Développement web
- `search` : Recherche
- `document` : Traitement de documents
- `text_to_image` : Génération d'images
- `text_to_video` : Génération de vidéos
- `image_edit` : Édition d'images
- `agent` : Agents

### Planification hebdomadaire

Pour surveiller les changements de classement chaque semaine :

```
Schedules → Add schedule
- Time: Monday 09:00 UTC
- Run input: {"mode":"changes","sources":["lmarena","epoch"],"categories":["text"],"maxItems":500}
```

Le mode `changes` ne renvoie que les entrées et changements depuis le dernier run.

### Sources et licences

- **LMArena Leaderboard Dataset** : https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset
  - Licence : **CC BY 4.0** (attribution requise)
  - API : Datasets Server HuggingFace (pas de clé requise)

- **Epoch AI Notable AI Models** : https://epoch.ai/data/ai-models
  - Licence : **CC BY 4.0** (attribution requise)
  - Format : CSV public

**Attribution obligatoire** : Chaque item inclut automatiquement les champs `attribution` et `source_url`.

### Tarification pay-per-event suggérée

- **Événement `record`** : 0,0001 $ par enregistrement
- **Événement `change-detected`** : 0,001 $ par changement détecté

### Limites

- **Pas de pagination automatique** : L'API HF Datasets Server renvoie max 100 rows par appel. Pour obtenir plus d'entrées, il faudrait implémenter la pagination avec `offset`.
- **Catégories en dur** : La liste des catégories disponibles peut évoluer côté LMArena.
- **Pas d'historique de rang** : L'acteur détecte les changements entre deux runs, mais ne construit pas de série temporelle complète.

# Actor input Schema

## `mode` (type: `string`):

snapshot = tous les classements normalisés ; changes = uniquement les différences depuis le dernier relevé

## `sources` (type: `array`):

Sources à interroger (au moins une requise)

## `categories` (type: `array`):

Catégories à inclure (vide = toutes). Ex: text, vision, webdev

## `maxItems` (type: `integer`):

Limite stricte du nombre d'enregistrements à produire

## `historyStoreName` (type: `string`):

Nom du store pour conserver l'historique entre runs

## `emitBaselineOnFirstRun` (type: `boolean`):

Au premier run en mode changes, émettre tous les items marqués is\_baseline=true (sinon 0 item)

## `snapshotRetention` (type: `integer`):

Nombre de relevés datés à garder dans l'historique (0 = désactivé)

## `webhookUrl` (type: `string`):

URL optionnelle pour recevoir un POST JSON avec le résumé des changements

## Actor input object example

```json
{
  "mode": "snapshot",
  "sources": [
    "lmarena"
  ],
  "categories": [
    "text"
  ],
  "maxItems": 1000,
  "historyStoreName": "llm-leaderboards-history",
  "emitBaselineOnFirstRun": true,
  "snapshotRetention": 7,
  "webhookUrl": ""
}
```

# Actor output Schema

## `results` (type: `string`):

Lien vers les items du dataset (entrées de classement et changements de rang)

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("rosmax/llm-leaderboards").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("rosmax/llm-leaderboards").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call rosmax/llm-leaderboards --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,rosmax/llm-leaderboards"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/oDSiNHASIh7HVQNuf/builds/xMEaVLyepIMPRb033/openapi.json