Frontier AI Models

The models shaping AI today

Proprietary and open-source frontier models — with benchmark scores, context windows, download links for local use, and pricing.

Data sources: LMSYS Chatbot Arena·HuggingFace Open LLM Leaderboard· Official model papers · Updated June 2026

Arena ELO = human preference ranking from blind A/B tests. MMLU = multi-subject knowledge. HumanEval = code generation. MATH = competition math. GPQA = PhD-level science.

12 models · click column headers to sort
ModelArena ELOMMLU %HumanEval %MATH %GPQA %ContextDownload / API
Claude Opus 4.7
Anthropic
1380
91.292.58278.4200K
$15/$75 per 1M tokens
1374
91.895.196.787.7200K
$10/$40 per 1M tokens
GPT-4.1
OpenAI
1368
90.59279.676.21M
$2/$8 per 1M tokens
Gemini 2.5 Pro
Google DeepMind
1360
90.990.291841M
$1.25/$10 per 1M tokens
Claude Sonnet 4.6
Anthropic
1352
90.190.878.374.1200K
$3/$15 per 1M tokens
DeepSeek R1
DeepSeek
1301
90.892.297.371.5128K
$0.55/$2.19 per 1M tokens
Gemini 2.5 Flash
Google DeepMind
1298
89.286.586.3751M
$0.15/$0.60 per 1M tokens
Llama 4 Maverick
Meta AI
1288
89.588.680.569.81M
Free/Free self-hosted
DeepSeek V3
DeepSeek
1262
88.589.98459.1128K
$0.27/$1.10 per 1M tokens
Qwen 3 72B
Alibaba Cloud
1255
88.987.785.365.2128K
Free/Free self-hosted
Llama 4 Scout
Meta AI
1241
87.883.274.161.41M
Free/Free self-hosted
Mistral Large 3
Mistral AI
1215
86.585.271.459.6128K
$2/$6 per 1M tokens

Run models locally

Tools to download and run open models

Run frontier open-source models on your own hardware — no API key, no data leaving your machine.

OllamaVisit

Run any open-source model with a single terminal command. `ollama run llama3.1:70b` — that's it. Ships with a local REST API compatible with OpenAI's client.

brew install ollama
Llama 3.1DeepSeek V3Qwen 2.5Phi-4Gemma 3
LLM StudioVisit

Desktop app with a beautiful GUI for discovering, downloading, and chatting with open models. Includes a local server mode. Best for non-technical users who want local AI.

Download from lmstudio.ai
All Llama modelsMistralDeepSeekPhi series
HuggingFaceVisit

The central hub for model weights, datasets, and papers. Download any model directly, explore the Open LLM Leaderboard, and find community fine-tunes for specific domains.

pip install transformers
Every open model500K+ checkpoints