API Documentation

Access benchmark data programmatically with our RESTful API

Quick Start

Base URL

https://benchmaxxed.ai

Example Request

curl -X GET "https://benchmaxxed.ai/api/benchmarks" \
  -H "Accept: application/json"

Response Format

All API responses are returned in JSON format with appropriate HTTP status codes.

Authentication

The API is currently open and does not require authentication for read operations. Rate limiting is applied to prevent abuse.

Rate Limits: 100 requests per minute per IP address

Endpoints

GET/api/benchmarks

Retrieve all available benchmarks

Parameters

Name	Type	Required	Description
`category`	string	Optional	Filter by category (e.g., 'Reasoning', 'Coding')
`limit`	number	Optional	Limit number of results (default: 100)
`offset`	number	Optional	Offset for pagination (default: 0)

Example Response

[
  {
    "id": "1",
    "name": "MMLU",
    "slug": "mmlu",
    "category": "Knowledge",
    "description": "Massive Multitask Language Understanding",
    "metrics": "Accuracy percentage",
    "explanation": "Tests knowledge across 57 subjects"
  }
]

Client Libraries

JavaScript/TypeScript

npm install @benchmaxxed/client

Python

pip install benchmaxxed

Go

go get github.com/benchmaxxed/go-client

Best Practices

Cache responses when possible to reduce API calls and improve performance
Use pagination parameters (limit/offset) for large datasets
Handle rate limiting gracefully with exponential backoff
Always check the response status code before processing data
Use appropriate Accept headers to specify the desired response format