ModelRefs / AI Model Categories
AI Model Categories
Every model category in the ModelRefs reference layer, with what each one covers and which published model profiles belong to it.
Overview
A category collects the model profiles that share a deployment shape and a set of trade-offs, so comparing inside one is comparing genuine alternatives rather than unrelated products.
Every category here has published profiles behind it. The profiles carry context windows, deployment options and the benchmark evidence recorded for that model, each with its source.
All model categories (10)
Each category collects the published model profiles that share a deployment shape and a set of trade-offs, so a comparison inside one is between genuine alternatives.
Large Language Models (LLMs)
Foundation models for text generation, reasoning, and conversation.
Best Coding AI Models
Models optimised for code generation, refactoring and debugging.
Best Open-Source AI Models
Models with public weights you can self-host and fine-tune.
Best Reasoning Models
Models that think step-by-step: math, logic, planning and analysis.
Best Multimodal AI Models
Models that natively understand images, text, audio and video.
Best Local LLMs (Run On Your Machine)
Open-weight models you can run privately on your own hardware.
Best Vision AI Models
Image generation, segmentation and visual understanding.
Best Audio AI Models
Transcription, voice cloning, TTS and music generation models.
Best Agentic AI Models
Models built for tool use, planning loops, and multi-step task execution.
Best Long-Context AI Models
Models that can process entire books, codebases, or transcripts in a single prompt.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to AI Model Categories.