"use client" import { Card, CardContent, CardDescription, CardHeader, CardTitle } from "@/components/ui/card" import { Badge } from "@/components/ui/badge" import { Separator } from "@/components/ui/separator" import { Button } from "@/components/ui/button" import Link from "next/link" import { ArrowLeft, ExternalLink, Sun, Moon } from "lucide-react" import { useTheme } from "next-themes" export default function AboutPage() { const { theme, setTheme } = useTheme() return (

About AI Evaluation Dashboard

A comprehensive platform for documenting and sharing AI system evaluations

Project Goals Our mission is to advance responsible AI development through transparent evaluation

Standardize AI Evaluation Reporting

Provide a consistent framework for documenting AI system capabilities and limitations across different models and platforms.

Facilitate Transparency

Enable AI developers and researchers to share detailed evaluation results in an accessible, standardized format.

Enable Comparative Analysis

Support side-by-side comparison of AI systems across multiple dimensions including capabilities and risks.

Support Research and Policy

Consolidate evaluation data to inform AI research directions and policy development.

Promote Responsible AI Development

Encourage comprehensive risk assessment and responsible deployment practices through structured evaluation.

{/* EvalEval link removed from page body per request; footer includes external link instead */} Standards and Frameworks Built on established international standards for AI evaluation
Risk Assessment

NIST AI 600-1

Risk categories are derived from the NIST AI Risk Management Framework (AI RMF 1.0), providing a comprehensive approach to identifying and managing AI-related risks.

Capabilities

OECD AI Classification

Capability categories are based on the OECD AI Classification Framework, ensuring alignment with international standards for AI system categorization.

For Contributors How to contribute to the evaluation framework

Schema-Driven Architecture

All evaluation categories, form fields, and data structures are centrally managed in the schema/ folder. This is the primary location for making structural changes to the evaluation framework.

schema/evaluation-schema.json - Evaluation categories and types
schema/output-schema.json - Complete data structure
schema/system-info-schema.json - Form field options
schema/category-details.json - Detailed descriptions

Adding Evaluations

Evaluation data files are stored in public/evaluations/ as JSON files. Each file represents a complete evaluation of an AI system and must conform to the schema.

AI Evaluation Dashboard is an open-source project dedicated to advancing responsible AI development — built with ❤️ by the EvalEval Coalition.

EvalEval Learn more about EvalEval: evalevalai.com

) }