adaptive-testing

Adaptive Testing Framework for AI Models (Psychometrics in AI Evaluation)

Adapting Questions to the student ability

Completely free, browser-based mockups of the HireVue's Cognitive Assessment tasks.

Score Impact Analyzer is a data-driven tool that simulates Digital SAT adaptive scoring to identify which missed questions have the highest impact on a student’s final score, helping optimize study focus for maximum improvement.

Research-grade adaptive capability profiling for autonomous AI agents using multidimensional IRT and information gain.

Claude Code skills that teach inside your zone of proximal development: adaptive testing finds your edge, an Obsidian vault keeps the learner model, and /tutor drills the gaps.

This project considers the use of p-value weighting to voxel-based lesion behavior mapping (VLSM) studies. Our methods are demonstrated on an aphasia study investigating which regions of the brain are associated with the severity of language impairment among stroke survivors.

Item Response Theory (IRT) — the framework behind adaptive tests like GRE and PTE. Designed for AI engineers and data scientists to grasp core IRT concepts for adaptive testing systems.

LMS platform with AI mentor: adaptive testing, LLM-powered code review, and HR interview simulation. Laravel + React + Kafka + Ollama.

IELTS, TOEFL iBT, and GRE practice platform built with Next.js, NestJS, Prisma, MySQL, Redis, and Docker. Includes timed mock exams, adaptive GRE testing, automated and AI-assisted scoring, speaking and writing workflows, autosave, test analytics, content management, secure media, role-based admin tools, and REST API documentation.

AI-powered adaptive IQ assessment platform featuring cognitive analysis, age-group calibration, skill-level profiling, adaptive difficulty adjustment, and multi-domain intelligence evaluation.

Item-response analysis of METR's AI time horizons, and HorizonCAT: cost-aware adaptive measurement of frontier agents

1D Adaptive Testing Engine using Item Response Theory (IRT) | FastAPI · MongoDB Atlas · GPT-4o-mini | Dynamically adjusts GRE question difficulty based on real-time ability estimation

Rasch (1PL) computerised adaptive testing engine: MLE scoring with a Bayesian fallback, maximum-information selection with exposure control, and a simulation showing 39% shorter tests at matched accuracy. No dependencies.

An adaptive testing backend built with FastAPI and MongoDB that dynamically adjusts question difficulty based on student performance and generates personalized study recommendations.

An adaptive testing engine: item response theory, maximum-information item selection, live ability estimation, and differential item functioning.

SmartTest — a Computerized Adaptive Testing (CAT) web app in PHP/MySQL where question difficulty adapts to candidate skill in real time

Rank LLMs with a fraction of the benchmark items, same ranking — adaptive (IRT/CAT) evaluation as a small, zero-dependency, drop-in Python library. The nanoGPT of adaptive LLM eval.

Adaptive GRE prep tool using 1PL IRT with Fisher Information item selection for real-time ability estimation. LLM generates personalized study plans with curated resources. Built with FastAPI, MongoDB Atlas, Clerk Auth, and OpenRouter. 74 tests, Docker support, structured logging.

Adaptive study PWA with a 3PL/EAP practice engine, SVG mechanics diagrams, content validation, and Supabase progress sync.