---
title: "LLM models and benchmarks"
description: "Track new AI models and read benchmarks correctly: what LLM benchmarks measure, how reasoning models differ, and a dated tracker of major model releases."
type: "topic-hub"
canonical_url: "https://theaiengineering.com/topics/models"
markdown_url: "https://theaiengineering.com/topics/models.md"
author: "The AI Engineering Editors"
publisher: "The AI Engineering"
keywords: ["llm benchmarks","new ai models","llm leaderboard","reasoning models","ai model comparison","open source llm"]
citation: "The AI Engineering Editors. \"LLM models and benchmarks.\" The AI Engineering. https://theaiengineering.com/topics/models"
---

# LLM models and benchmarks

What new models change, how to read benchmarks, and a dated release record.

New models ship every few weeks, and each release changes what is possible, what it costs and which benchmarks matter. Reading those changes well means knowing what a benchmark actually measures and where it stops being informative.

This hub explains benchmarks and leaderboards, reasoning models and test-time compute, and keeps a dated release tracker linked to each lab's own announcement.

## LLM models and benchmarks guides

- [Best LLM for coding: models compared on agentic coding benchmarks](https://theaiengineering.com/articles/best-llm-for-coding): The best LLM for coding depends on the job: 11 models compared on Terminal-Bench 4.0, DeepSWE, and SWE-bench Pro, plus context, open weights, and cost.
- [Reasoning models: how they work and when to use them](https://theaiengineering.com/articles/reasoning-models): Reasoning models explained: how test-time compute and reinforcement learning produce chain-of-thought reasoning, when to use them, and their cost and latency.
- [LLM benchmarks explained: what they measure and how to read them](https://theaiengineering.com/articles/llm-benchmarks): LLM benchmarks explained: what MMLU-Pro, GPQA, SWE-bench, LiveCodeBench, ARC-AGI, and LMArena measure, why scores saturate, and how to read a leaderboard.

## Key terms

- [Benchmark contamination](https://theaiengineering.com/glossary/benchmark-contamination): Benchmark contamination is the presence of a benchmark's test questions, answers, or solutions in a model's training data, so its score can reflect memorization instead of the capability the benchmark measures.
- [Direct preference optimization](https://theaiengineering.com/glossary/direct-preference-optimization): Direct preference optimization (DPO) is a fine-tuning method that trains a language model on pairs of preferred and rejected responses with a simple classification loss, without the reward model and reinforcement learning that RLHF needs.
- [Fine-tuning](https://theaiengineering.com/glossary/fine-tuning): Fine-tuning is the process of further training a pretrained model on a smaller, task-specific dataset so its weights change to improve performance on a particular task, domain, style, or output format.
- [Knowledge distillation](https://theaiengineering.com/glossary/knowledge-distillation): Knowledge distillation is a model compression technique in which a smaller student model is trained to reproduce the outputs or output probabilities of a larger, more capable teacher model.
- [Large language model (LLM)](https://theaiengineering.com/glossary/large-language-model): A large language model (LLM) is a neural network, usually a transformer with billions of parameters, trained on web-scale text to predict the next token and then adapted to follow instructions.
- [LMArena](https://theaiengineering.com/glossary/lmarena): LMArena, originally Chatbot Arena and branded Arena since January 2026, is a public leaderboard that ranks language models from crowdsourced human votes between pairs of anonymous model responses.
- [LoRA](https://theaiengineering.com/glossary/lora): LoRA (low-rank adaptation) is a parameter-efficient fine-tuning method that freezes a pretrained model's weights and trains small low-rank matrices added to selected layers, cutting trainable parameters and memory use.
- [Mixture of experts](https://theaiengineering.com/glossary/mixture-of-experts): Mixture of experts (MoE) is a neural network architecture in which a learned router sends each token to a few specialized subnetworks, called experts, so only part of the model runs per token.
- [MMLU](https://theaiengineering.com/glossary/mmlu): MMLU (Massive Multitask Language Understanding) is a benchmark of 15,908 four-option multiple-choice questions across 57 subjects, from elementary mathematics to law, that measures a language model's broad academic knowledge.
- [Multimodal model](https://theaiengineering.com/glossary/multimodal-model): A multimodal model is an AI model that takes in or produces more than one type of data, such as text, images, audio, or video, and combines them within a single model.
- [Open-weights model](https://theaiengineering.com/glossary/open-weights-model): An open-weights model is an AI model whose trained parameters are published for download, so anyone can run, fine-tune, or quantize it on their own hardware under the terms of its license.
- [pass@k](https://theaiengineering.com/glossary/pass-at-k): pass@k is an evaluation metric that estimates the probability that at least one of k sampled outputs for a task passes its tests, used mainly in code generation and agent benchmarks.
- [Pretraining](https://theaiengineering.com/glossary/pretraining): Pretraining is the first stage of training a language model, in which it learns to predict the next token across a large unlabeled corpus of text and code, producing a general-purpose base model.
- [Reasoning model](https://theaiengineering.com/glossary/reasoning-model): A reasoning model is a large language model trained, usually with reinforcement learning, to generate intermediate reasoning tokens before its final answer, spending more inference compute to solve multi-step problems.
- [RLHF](https://theaiengineering.com/glossary/rlhf): RLHF (reinforcement learning from human feedback) is a fine-tuning method that trains a reward model on human rankings of model outputs, then optimizes the language model with reinforcement learning to score highly.
- [Small language model](https://theaiengineering.com/glossary/small-language-model): A small language model (SLM) is a language model compact enough to run on a consumer device such as a laptop or phone, which in 2025 generally meant fewer than about 10 billion parameters.
- [SWE-bench](https://theaiengineering.com/glossary/swe-bench): SWE-bench is a benchmark of 2,294 real GitHub issues from 12 Python repositories, in which a model or agent must write a patch that resolves the issue and passes the repository's tests.
- [Test-time compute](https://theaiengineering.com/glossary/test-time-compute): Test-time compute is the computation a language model spends while answering a query, through longer reasoning, multiple samples, or search, as opposed to the train-time compute spent building the model.
- [Transformer](https://theaiengineering.com/glossary/transformer): A transformer is a neural network architecture that processes sequences with self-attention, letting each token weigh information from other tokens in parallel; it is the basis of most modern large language models.

## Tools and platforms

- [Model providers](https://theaiengineering.com/platforms/model-providers): 38 platforms. A model provider is a company or research lab that trains large language models and makes them available through a hosted API, downloadable open weights, or both.
- [Fine-tuning and post-training](https://theaiengineering.com/platforms/fine-tuning): 30 platforms. Fine-tuning tools adapt a pretrained language model to a task, domain, or style by continuing training on new examples, through supervised fine-tuning, preference optimization such as DPO, or reinforcement learning with methods such as GRPO.

## Cite this page

The AI Engineering Editors. "LLM models and benchmarks." The AI Engineering. https://theaiengineering.com/topics/models

- Title: LLM models and benchmarks
- Author: The AI Engineering Editors
- Publisher: The AI Engineering
- URL: https://theaiengineering.com/topics/models
- Markdown: https://theaiengineering.com/topics/models.md
