New: connect Claude & other AIs to GenAIList over MCP โ research the catalog and contribute to the shared knowledge base. Learn how โ
Large language models (LLMs)
Browse every major large language model in one place. This LLM list tracks frontier and open-source foundation models โ GPT, Claude, Gemini, Llama, Mistral, Qwen and 400+ more โ with parameter counts, context windows, benchmark scores and provider pricing.
Llemma 34B
๐บ๐ธ Princeton University
Llemma 7B
๐บ๐ธ Princeton University
Aquila2 34B
๐จ๐ณ Beijing Academy of Artificial Intelligence / BAAI
Table-GPT
๐บ๐ธ Microsoft Research
Jiutian
๐บ๐ธ China Mobile
CELLE-2
๐บ๐ธ Chan Zuckerberg Initiative
CodeFuse-13B
๐จ๐ณ Ant Group
Mistral 7B
๐ซ๐ท Mistral AI
RoseTTAFold All-Atom (RFAA)
๐บ๐ธ University of Washington
FinGPT-13B
๐บ๐ธ University of California Los Angeles (UCLA)
NAEPro
๐บ๐ธ University of California Santa Barbara (UCSB)
FoldFlow
๐บ๐ธ McGill University
LLaMA-7B (protein-oriented instruction-tuned)
๐บ๐ธ Zhejiang University (ZJU)
MiniGPT4 (Vicuna finetune)
๐บ๐ธ King Abdullah University of Science and Technology (KAUST)
New Intelligent Q&A
Unknown
Phi-1
๐บ๐ธ Microsoft Research
CTM (CIFAR-10)
๐บ๐ธ Stanford University
TinyLlama-1.1B (1T token checkpoint)
๐ธ๐ฌ Singapore University of Technology & Design
TinyLlama-1.1B (3T token checkpoint)
๐ธ๐ฌ Singapore University of Technology & Design
PIXART-ฮฑ
๐จ๐ณ Huawei Noah's Ark Lab
StableLM-3B-4E1T
๐บ๐ธ Stability AI
Wuerstchen
๐บ๐ธ Technische Hochschule Ingolstadt
Amazon Titan
๐บ๐ธ Amazon
PLaMo-13B
๐ฏ๐ต Preferred Networks Inc
Qwen-14B
๐จ๐ณ Qwen
Qwen-7B
๐จ๐ณ Qwen
BigRNA
๐จ๐ฆ DeepGenomics
Emu (Meta)
๐บ๐ธ Meta AI
AlphaMissense
๐บ๐ธ Google DeepMind
PengCheng Mind (้นๅ่ๆตท)
๐บ๐ธ Peng Cheng Laboratory
BTLM-3B
๐บ๐ธ Cerebras Systems
Baichuan 2-7B
๐จ๐ณ Baichuan
GPT-MolBERTa
๐บ๐ธ Carnegie Mellon University (CMU)
OpenChat-13b
๐จ๐ณ Tsinghua University
bge-reranker-large
๐จ๐ณ Beijing Academy of Artificial Intelligence / BAAI
DeciLM 6B
๐ฎ๐ฑ Deci AI
Phi-1.5
๐บ๐ธ Microsoft
MADLAD-400 10B
๐บ๐ธ Google DeepMind
FLM-101B
๐จ๐ณ Chinese Academy of Sciences
Hunyuan
๐จ๐ณ Tencent
Persimmon-8B
๐บ๐ธ Adept
XGen-7B
๐บ๐ธ Salesforce
Baichuan2-13B
๐จ๐ณ Baichuan
Falcon-180B
๐ฆ๐ช Technology Innovation Institute
TigerBot-70B
๐จ๐ณ Tigerobo
Cerbero 7B
๐ฎ๐น University of Pisa
ABAB
๐จ๐ณ MiniMax
Jais
๐บ๐ธ Cerebras Systems
Refact-1.6B
๐ฌ๐ง Refact AI
PeptideBERT
๐บ๐ธ Carnegie Mellon University (CMU)
Mengzi-Fin-13B
๐จ๐ณ Langboat
Mengzi-Fin-7B
๐จ๐ณ Langboat
MengziGPT-General-40B
๐จ๐ณ Langboat
Mengzi-Lite
๐จ๐ณ Langboat
Open-Assistant Llama2 70B SFT v10
Unknown
HyperCLOVA X
๐ฐ๐ท NAVER
MathGPT
๐จ๐ณ TAL Education Group (Xueersi)
airoboros-l2-70b-2.1
Unknown
PULI GPTrio
๐ญ๐บ Hungarian Research Centre for Linguistics
ShapeMol
๐บ๐ธ Ohio State University
About Large language models (LLMs)
Large language models (LLMs) are the foundation of modern generative AI โ general-purpose text models trained on vast corpora that can write, reason, summarise, translate and code. Choosing the best LLM is rarely about a single winner: the best AI model for one task may lag on another. Reasoning-heavy work rewards models that score well on benchmarks like MMLU, GPQA and AIME, while agentic and tool-use workloads care more about instruction following, function calling and long-context recall. When you compare LLMs, weigh raw capability against the practical constraints that decide cost and feasibility โ context window, throughput, latency, licensing and price per million tokens. Open-source LLMs such as Llama, Qwen, Mistral and DeepSeek let you self-host and fine-tune, while proprietary frontier models from OpenAI, Anthropic and Google often lead on raw quality. Use our benchmarks to see where each model ranks, and put two candidates side by side with compare before you commit to a provider.
Frequently asked questions
What is the best LLM right now?
There is no single best LLM โ it depends on the task. Frontier proprietary models from OpenAI, Anthropic and Google tend to lead on reasoning benchmarks, while open-source LLMs like Llama, Qwen and DeepSeek are best when you need to self-host or fine-tune. Compare candidates on the benchmarks page for your specific workload.
What is the best open source LLM?
The strongest open-source and open-weights LLMs at any given time typically come from the Llama, Qwen, Mistral and DeepSeek families. They can be downloaded, self-hosted and fine-tuned, and the top ones rival proprietary models on many benchmarks. Filter the list above by availability to see current open-weights options.
How do I compare two LLMs?
Use the compare tool to put two models side by side on parameters, context window, availability and benchmark scores, then check the benchmarks page for task-specific rankings such as MMLU, GPQA and coding scores.