Chat & assistants

General-purpose assistants for writing, research, analysis and everyday questions: the frontier models, the apps that wrap them, and the runtimes that let you chat with open models on your own machine.

Models are ranked by LMArena Text Arena (overall, style control), then Artificial Analysis Intelligence Index for models without a result on the first. Tools inherit the tier of the best model they offer. How we rank.

Best overallSGemini 4 Argon1,524 on LMArena Text Arena (overall, style control)
Best valueAMiMo-V2.6-FlashTier A for $0.18/M tokens
Best free startSGeminiFree tier · from $4.99/mo · via Gemini 4 Argon
Best local (≤24 GB GPU)AGemma 4 (31B)~19 GB VRAM · 1,452 on LMArena Text Arena (overall, style control)

Tier: how close to the best result on the task's main public benchmark
Outlined: a tool inherits the tier of the best model it offers
No public result yet
Cloud · Local: runs on your own hardware

Models

The engines themselves. Use them through an API or inside the apps on the right.

Cloud

Gemini 4 ArgonGoogle · $4/M tokens1,524 on LMArena Text Arena (overall, style control)$S Muse WonderMeta · $8/M tokens1,509 on LMArena Text Arena (overall, style control)S

Claude Opus 5.5Anthropic · $8/M tokens1,508 on LMArena Text Arena (overall, style control)S

Claude Fable 5.1Anthropic · $20/M tokens1,502 on LMArena Text Arena (overall, style control)S

Gemini 3.8 FlashGoogle · $1.5/M tokens1,496 on LMArena Text Arena (overall, style control)$S Muse Spark 1.3Meta · $2/M tokens1,494 on LMArena Text Arena (overall, style control)S

Gemini 3.1 Pro (Preview)Google · $4.5/M tokens1,487 on LMArena Text Arena (overall, style control)S

GPT-6.1 SolOpenAI · $4/M tokens1,484 on LMArena Text Arena (overall, style control)A Qwen3.8-MaxAlibaba (Qwen) · $3/M tokens1,482 on LMArena Text Arena (overall, style control)A

GPT-6 AstraOpenAI · $20/M tokens1,477 on LMArena Text Arena (overall, style control)A

Claude Sonnet 5.5Anthropic · $4/M tokens1,475 on LMArena Text Arena (overall, style control)A

ERNIE 5.1Baidu1,467 on LMArena Text Arena (overall, style control)A

Qwen3.7-PlusAlibaba (Qwen) · $0.56/M tokens1,456 on LMArena Text Arena (overall, style control)$A

Gemini 3.5 Flash-LiteGoogle · $0.85/M tokens1,455 on LMArena Text Arena (overall, style control)A

Grok 4.7xAI · $3/M tokens1,444 on LMArena Text Arena (overall, style control)A

GPT-6 LunaOpenAI · $0.2/M tokens1,443 on LMArena Text Arena (overall, style control)$A

Mistral Large 4 (preview)Mistral AI · $2.06/M tokens1,432 on LMArena Text Arena (overall, style control)B

Solar Pro 4Upstage · $0.52/M tokens1,386 on LMArena Text Arena (overall, style control)B

Claude Haiku 5.5Anthropic · $0.2/M tokens43 on Artificial Analysis Intelligence Index C

Mercury 2.5Inception · $0.34/M tokens12 on Artificial Analysis Intelligence Index –

Seed 2.1 ProByteDance SeedNo public result yet

Local

Kimi K3Moonshot AI · ~1600 GB VRAM1,487 on LMArena Text Arena (overall, style control)$A

MiMo-V2.6-ProXiaomi · ~585 GB VRAM1,479 on LMArena Text Arena (overall, style control)$A

GLM-5.3Z.ai · ~425 GB VRAM1,479 on LMArena Text Arena (overall, style control)$A

DeepSeek-V4.1-Flash-1017DeepSeek · ~320 GB VRAM1,475 on LMArena Text Arena (overall, style control)$A

GLM-5.3-FlashZ.ai · ~185 GB VRAM1,474 on LMArena Text Arena (overall, style control)$A

DeepSeek-V4-Pro-0813DeepSeek · ~920 GB VRAM1,465 on LMArena Text Arena (overall, style control)A

Gemma 4 (31B)Google DeepMind · ~19 GB VRAM1,452 on LMArena Text Arena (overall, style control)$A

MiMo-V2.6-FlashXiaomi · ~178 GB VRAM1,451 on LMArena Text Arena (overall, style control)A

Step 5 PreviewStepFun · ~346 GB VRAM1,447 on LMArena Text Arena (overall, style control)A

MiniMax-M3MiniMax · ~245 GB VRAM1,441 on LMArena Text Arena (overall, style control)A

InklingThinking Machines Lab · ~557 GB VRAM1,441 on LMArena Text Arena (overall, style control)A

Qwen3.8-27BAlibaba (Qwen) · ~17 GB VRAM1,438 on LMArena Text Arena (overall, style control)$A

Mistral Medium 3.5Mistral AI · ~75 GB VRAM1,426 on LMArena Text Arena (overall, style control)A

Nemotron 3 Ultra 550B-A55BNVIDIA · ~321 GB VRAM1,426 on LMArena Text Arena (overall, style control)A

Muse Glimmer 30BMeta · ~19 GB VRAM1,425 on LMArena Text Arena (overall, style control)B

Nemotron 3.5 Super VL 120B-A12BNVIDIA · ~72 GB VRAM1,416 on LMArena Text Arena (overall, style control)B

Inkling SmallThinking Machines Lab · ~159 GB VRAM1,404 on LMArena Text Arena (overall, style control)B

Trinity Large ThinkingArcee AI · ~229 GB VRAM1,367 on LMArena Text Arena (overall, style control)B

Ling-3.1-flashinclusionAI (Ant Group) · ~321 GB VRAM41 on Artificial Analysis Intelligence Index B

gpt-oss-120bOpenAI · ~80 GB VRAM1,352 on LMArena Text Arena (overall, style control)B

Nemotron 3.5 Lightning 30B-A3BNVIDIA · ~20 GB VRAM1,351 on LMArena Text Arena (overall, style control)B

Qwen3.8-2.4T-A95BAlibaba (Qwen) · ~1370 GB VRAM40 on Artificial Analysis Intelligence Index B

Qwen3.8-Flash-NextAlibaba (Qwen) · ~104 GB VRAM40 on Artificial Analysis Intelligence Index C

Granite 4.2 30BIBM · ~18 GB VRAM1,340 on LMArena Text Arena (overall, style control)C

Muse Spark Open (816B-A42B)Meta · ~470 GB VRAM39 on Artificial Analysis Intelligence Index C

Olmo 3.1 32BAllen Institute for AI (Ai2) · ~20 GB VRAM1,329 on LMArena Text Arena (overall, style control)C

Llama 4 MaverickMeta · ~230 GB VRAM1,327 on LMArena Text Arena (overall, style control)C

gpt-oss-20bOpenAI · ~16 GB VRAM1,317 on LMArena Text Arena (overall, style control)$C

Motif-3Motif Technologies · ~181 GB VRAM34 on Artificial Analysis Intelligence Index C

K2-Horizon-375B-A23BMBZUAI Institute of Foundation Models · ~218 GB VRAM31 on Artificial Analysis Intelligence Index C

Beam 1.0 (501B-A23B)Reflection AI · ~287 GB VRAM30 on Artificial Analysis Intelligence Index C

Kimi K2.7 CodeMoonshot AI · ~587 GB VRAM26 on Artificial Analysis Intelligence Index C

K2-Horizon-MoVA-36B-A4BMBZUAI Institute of Foundation Models · ~23 GB VRAM25 on Artificial Analysis Intelligence Index C

Solar Open2 250BUpstage · ~144 GB VRAM25 on Artificial Analysis Intelligence Index C

A.X K2SK Telecom · ~396 GB VRAM21 on Artificial Analysis Intelligence Index C

Nemotron 3.5 Bolt 74B-A9BNVIDIA · ~24 GB VRAM21 on Artificial Analysis Intelligence Index C

K-EXAONE 2.0 (750B-A37B)LG AI Research · ~428 GB VRAM20 on Artificial Analysis Intelligence Index C

LongCat-2.0Meituan (LongCat) · ~1014 GB VRAM19 on Artificial Analysis Intelligence Index C

Command A+ (05-2026)Cohere · ~126 GB VRAM13 on Artificial Analysis Intelligence Index C

Ministral 3 14B (2512)Mistral AI · ~9 GB VRAM6 on Artificial Analysis Intelligence Index$C

Mistral Small 4 (2603)Mistral AI · ~69 GB VRAM11 on Artificial Analysis Intelligence Index C

Ring-2.6-1TinclusionAI (Ant Group) · ~586 GB VRAM17 on Artificial Analysis Intelligence Index C

Sarvam-105BSarvam AI · ~62 GB VRAM9 on Artificial Analysis Intelligence Index –

Hy4-previewTencent · ~441 GB VRAMNo public result yet –

Laguna M.1Poolside · ~130 GB VRAMNo public result yet –

LFM2.5-24B-A2BLiquid AI · ~15 GB VRAMNo public result yet

Apps

Ready-made apps with a UI: sign in or install, then start.

Cloud

ChatLLMAbacus.AI · $10/movia Gemini 4 Argon S

GeminiGoogle · Free tier · $4.99/movia Gemini 4 Argon$S

MammouthMammouth AIvia Gemini 4 Argon S

PerplexityPerplexity AI · Free tier · $20/movia Gemini 4 Argon S

VeniceVenice.ai · Free tier · $18/movia Gemini 4 Argon S

PoeQuora · Free tiervia Muse Wonder S ChatWiseChatWisevia Claude Opus 5.5 S

ClaudeAnthropic · Free tier · $20/movia Claude Opus 5.5 S

Google AI StudioGoogle · Freevia Gemini 3.8 Flash$S

Meta AIMeta · Free tiervia Muse Spark 1.3 S HuggingChatHugging Face · Free tier · $9/movia Kimi K3 S

Kagi AssistantKagi · Free tier · $5/movia Gemini 3.1 Pro (Preview)S

KimiMoonshot AI · Free tiervia Kimi K3 S

ChatGPTOpenAI · Free tier · $20/movia GPT-6.1 Sol S Microsoft CopilotMicrosoft · Free tier · $9.99/movia GPT-6.1 Sol A

Z.ai ChatZ.aivia GLM-5.3-Flash A Wenxin Assistant (ERNIE Bot)Baiduvia ERNIE 5.1 A

DeepSeekDeepSeek · Freevia DeepSeek-V4-Pro-0813 A

YuanbaoTencent · Freevia DeepSeek-V4-Pro-0813 A

Duck.aiDuckDuckGo · Free tiervia Gemma 4 (31B)A

GrokSpaceXSI (formerly xAI) · Free tier · $8/movia Grok 4.7 A

Vibe (formerly Le Chat)Mistral AI · Free tier · $15/movia Mistral Medium 3.5 B

Qwen ChatAlibaba (Qwen team) · Freevia Qwen3.8-2.4T-A95B –

Alexa+Amazon · Free tier · $20/moNo public result yet –

DoubaoByteDance · Free tierNo public result yet –

iFlytek Spark (Xinghuo)iFlytekNo public result yet –

LumoProton · Free tier · $13/moNo public result yet –

MonicaMonicaNo public result yet

Local

Open WebUIOpen WebUI Inc. · Freevia Kimi K3$S

NextChatNextChat · Freevia Kimi K3$S

LobeHub (formerly LobeChat)LobeHub · Free tier · $9.9/movia Kimi K3 S

AnythingLLMMintplex Labs · Freevia Kimi K3$S

Cherry StudioCherryHQ · Freevia Kimi K3$S

TextGen (text-generation-webui)oobabooga · Freevia Kimi K3$S

LibreChatLibreChat · Freevia Kimi K3$S

JanMenlo Research · Freevia Kimi K3$S

ChatboxChatbox AI · Free tier · $3.99/movia Kimi K3 S

KhojKhoj · Freevia Kimi K3$S

Big-AGIBig-AGI · Freevia Kimi K3$S

DeepChatThinkInAI · Freevia Kimi K3$S

5irenanbingxyz · Freevia Kimi K3$S

WitsyKochava Studios · Freevia Kimi K3$S

LM StudioElement Labs · Freevia Kimi K3$S

Msty StudioMsty · Freevia Kimi K3$A

Unsloth (Studio / Desktop app)Unsloth AI · Freevia DeepSeek-V4.1-Flash-1017 A

Page Assistn4ze3m · Freevia GLM-5.3-Flash A

OsaurusOsaurus · Freevia GLM-5.3-Flash A

Enchantedgluonfield · Freevia GLM-5.3-Flash A AlpacaJeffser · Freevia GLM-5.3-Flash A

BoltAIBoltAIvia GLM-5.3-Flash A

TypingMindTypingMindvia GLM-5.3-Flash A

Google AI Edge GalleryGoogle · Freevia Gemma 4 (31B)A

PocketPal AIa-ghorbani · Freevia Gemma 4 (31B)A

ChatterUIVali-98 · Freevia Gemma 4 (31B)A

MaidMobile Artificial Intelligence · Freevia Gemma 4 (31B)A

Llamaggml-org and Hugging Face · Freevia Gemma 4 (31B)A

Locally AIElement Labs (LM Studio)via Gemma 4 (31B)–

Brave LeoBrave · Free tier · $15/moNo public result yet

Runtimes & gateways

Run open models on your own machine, or reach many models through one API.

Cloud

Gemini Enterprise Agent Platform (formerly Vertex AI)Google Cloudvia Gemini 4 Argon S

OpenRouterOpenRouter · Free tiervia Gemini 4 Argon S

PerplexityPerplexity AI · Free tier · $20/movia Gemini 4 Argon$S

RequestyRequestyvia Gemini 4 Argon S

Vercel AI GatewayVercel · Free tiervia Gemini 4 Argon S

Amazon BedrockAmazon Web Servicesvia Claude Opus 5.5 S

DeepInfraDeepInfravia Claude Opus 5.5 S

Microsoft FoundryMicrosoftvia Claude Fable 5.1 S

Fireworks AIFireworks AIvia Kimi K3 S

Hugging Face Inference ProvidersHugging Face · Free tier · $9/movia Kimi K3$S

Novita AINovita AIvia Kimi K3 S

Together AITogether AIvia Kimi K3 A

Cloudflare Workers AICloudflare · Free tiervia GLM-5.3 A

NVIDIA NIM APIs (build.nvidia.com)NVIDIA · Free tiervia GLM-5.3 A

SambaNova CloudSambaNovavia Gemma 4 (31B)A

Cerebras InferenceCerebras · Free tiervia Qwen3.8-27B A

GroqGroqvia Qwen3.8-27B

Local

OllamaOllama · Freevia Kimi K3$S

llama.cppggml-org · Freevia Kimi K3$S

vLLMvLLM project · Freevia Kimi K3$S

LiteLLMBerriAI · Freevia Kimi K3$S

LocalAIEttore Di Giacinto (mudler) · Freevia Kimi K3$S

exoEXO Labs · Freevia Kimi K3$S

SGLangSGLang project (LMSYS) · Freevia Kimi K3$S KTransformersKVCache.AI (Tsinghua MADSys) · Freevia Kimi K3$S

TensorRT LLMNVIDIA · Freevia Kimi K3$S

Portkey AI GatewayPortkey · Freevia Kimi K3$S

XinferenceXorbits · Freevia Kimi K3$S

LMDeployInternLM (Shanghai AI Laboratory) · Freevia Kimi K3$S

MLX LMApple (ml-explore) · Freevia Kimi K3$S

GPUStackGPUStack · Freevia Kimi K3$A

llamafileMozilla.ai · Freevia GLM-5.3-Flash A

LLM (CLI)Simon Willison · Freevia GLM-5.3-Flash A

AIChatsigoden · Freevia GLM-5.3-Flash A

mistral.rsEric Buehler · Freevia GLM-5.3-Flash A

llama-swapmostlygeek · Freevia GLM-5.3-Flash A

LemonadeAMD (lemonade-sdk) · Freevia GLM-5.3-Flash A

RamaLamaRamaLama project (containers) · Freevia GLM-5.3-Flash A

TabbyAPI (ExLlamaV3)theroyallab · Freevia GLM-5.3-Flash A

Docker Model RunnerDocker · Freevia GLM-5.3-Flash A

MLC LLMMLC AI · Freevia Gemma 4 (31B)A

WebLLMMLC AI · Freevia Gemma 4 (31B)A GenieXQualcomm · Freevia Gemma 4 (31B)C

Foundry LocalMicrosoft · Freevia gpt-oss-20b

Quality vs. price

LMArena Text Arena (overall, style control) score against API price (USD per 1M tokens, blended 3:1 input:output, log scale). Up and to the left is better; the line joins the models that nothing else beats on both.

Closed models
Open-weights models
Best-value frontier

Show as table

Model	Weights	LMArena Text Arena (overall, style control)	Price	Frontier
Gemini 4 Argon	Closed	1,524	$4/M tokens	Yes
Muse Wonder	Closed	1,509	$8/M tokens
Claude Opus 5.5	Closed	1,508	$8/M tokens
Claude Fable 5.1	Closed	1,502	$20/M tokens
Gemini 3.8 Flash	Closed	1,496	$1.5/M tokens	Yes
Muse Spark 1.3	Closed	1,494	$2/M tokens
Kimi K3	Open	1,487	$6/M tokens
Gemini 3.1 Pro (Preview)	Closed	1,487	$4.5/M tokens
GPT-6.1 Sol	Closed	1,484	$4/M tokens
Qwen3.8-Max	Closed	1,482	$3/M tokens
MiMo-V2.6-Pro	Open	1,479	$0.54/M tokens	Yes
GLM-5.3	Open	1,479	$2.15/M tokens
GPT-6 Astra	Closed	1,477	$20/M tokens
Claude Sonnet 5.5	Closed	1,475	$4/M tokens
DeepSeek-V4.1-Flash-1017	Open	1,475	$0.52/M tokens	Yes
GLM-5.3-Flash	Open	1,474	$0.24/M tokens	Yes
DeepSeek-V4-Pro-0813	Open	1,465	$1.98/M tokens
Qwen3.7-Plus	Closed	1,456	$0.56/M tokens
Gemini 3.5 Flash-Lite	Closed	1,455	$0.85/M tokens
Gemma 4 (31B)	Open	1,452	$0.21/M tokens	Yes
MiMo-V2.6-Flash	Open	1,451	$0.18/M tokens	Yes
Step 5 Preview	Open	1,447	$1.43/M tokens
Grok 4.7	Closed	1,444	$3/M tokens
GPT-6 Luna	Closed	1,443	$0.2/M tokens
MiniMax-M3	Open	1,441	$0.52/M tokens
Inkling	Open	1,441	$1.76/M tokens
Qwen3.8-27B	Open	1,438	$0.96/M tokens
Mistral Large 4 (preview)	Closed	1,432	$2.06/M tokens
Mistral Medium 3.5	Open	1,426	$3/M tokens
Nemotron 3 Ultra 550B-A55B	Open	1,426	$1.05/M tokens
Muse Glimmer 30B	Open	1,425	$0.52/M tokens
Nemotron 3.5 Super VL 120B-A12B	Open	1,416	$0.18/M tokens
Inkling Small	Open	1,404	$0.64/M tokens
Solar Pro 4	Closed	1,386	$0.52/M tokens
Trinity Large Thinking	Open	1,367	$0.39/M tokens
gpt-oss-120b	Open	1,352	$0.26/M tokens
Nemotron 3.5 Lightning 30B-A3B	Open	1,351	$0.1/M tokens	Yes
Llama 4 Maverick	Open	1,327	$0.55/M tokens
gpt-oss-20b	Open	1,317	$0.13/M tokens

Everything, in order

All chat & assistants options in quality order
Tier	Name	Approach	Runs	Rated by	Price	Skill
S	Gemini 4 Argon Google	Models	Cloud	1,524 on LMArena Text Arena (overall, style control)	$4/M tokens	—
S	Muse Wonder Meta	Models	Cloud	1,509 on LMArena Text Arena (overall, style control)	$8/M tokens	—
S	Claude Opus 5.5 Anthropic	Models	Cloud	1,508 on LMArena Text Arena (overall, style control)	$8/M tokens	—
S	Claude Fable 5.1 Anthropic	Models	Cloud	1,502 on LMArena Text Arena (overall, style control)	$20/M tokens	—
S	Gemini 3.8 Flash Google	Models	Cloud	1,496 on LMArena Text Arena (overall, style control)	$1.5/M tokens	—
S	Muse Spark 1.3 Meta	Models	Cloud	1,494 on LMArena Text Arena (overall, style control)	$2/M tokens	—
S	Gemini 3.1 Pro (Preview) Google	Models	Cloud	1,487 on LMArena Text Arena (overall, style control)	$4.5/M tokens	—
S	Kimi K3 Moonshot AI	Models	Local	1,487 on LMArena Text Arena (overall, style control)	~1600 GB VRAM	—
S	GPT-6.1 Sol OpenAI	Models	Cloud	1,484 on LMArena Text Arena (overall, style control)	$4/M tokens	—
S	ChatLLM Abacus.AI	Apps	Cloud	via Gemini 4 Argon	$10/mo	beginner
S	Gemini Google	Apps	Cloud	via Gemini 4 Argon	Free tier · $4.99/mo	beginner
S	Gemini Enterprise Agent Platform (formerly Vertex AI) Google Cloud	Runtimes & gateways	Cloud	via Gemini 4 Argon	—	advanced
S	Mammouth Mammouth AI	Apps	Cloud	via Gemini 4 Argon	—	beginner
S	OpenRouter OpenRouter	Runtimes & gateways	Cloud	via Gemini 4 Argon	Free tier	intermediate
S	Perplexity Perplexity AI	Apps + Runtimes & gateways	Cloud	via Gemini 4 Argon	Free tier · $20/mo	beginner
S	Requesty Requesty	Runtimes & gateways	Cloud	via Gemini 4 Argon	—	intermediate
S	Venice Venice.ai	Apps	Cloud	via Gemini 4 Argon	Free tier · $18/mo	beginner
S	Vercel AI Gateway Vercel	Runtimes & gateways	Cloud	via Gemini 4 Argon	Free tier	intermediate
S	Poe Quora	Apps	Cloud	via Muse Wonder	Free tier	beginner
S	Amazon Bedrock Amazon Web Services	Runtimes & gateways	Cloud	via Claude Opus 5.5	—	advanced
S	ChatWise ChatWise	Apps	Cloud	via Claude Opus 5.5	—	beginner
S	Claude Anthropic	Apps	Cloud	via Claude Opus 5.5	Free tier · $20/mo	beginner
S	DeepInfra DeepInfra	Runtimes & gateways	Cloud	via Claude Opus 5.5	—	intermediate
S	Microsoft Foundry Microsoft	Runtimes & gateways	Cloud	via Claude Fable 5.1	—	advanced
S	Google AI Studio Google	Apps	Cloud	via Gemini 3.8 Flash	Free	intermediate
S	Meta AI Meta	Apps	Cloud	via Muse Spark 1.3	Free tier	beginner
S	Ollama Ollama	Runtimes & gateways	Local	via Kimi K3	Free	intermediate
S	Open WebUI Open WebUI Inc.	Apps	Local	via Kimi K3	Free	intermediate
S	llama.cpp ggml-org	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	vLLM vLLM project	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	NextChat NextChat	Apps	Local	via Kimi K3	Free	intermediate
S	LobeHub (formerly LobeChat) LobeHub	Apps	Local	via Kimi K3 Cloud models: tier S	Free tier · $9.9/mo	intermediate
S	AnythingLLM Mintplex Labs	Apps	Local	via Kimi K3	Free	beginner
S	LiteLLM BerriAI	Runtimes & gateways	Local	via Kimi K3 Cloud models: tier S	Free	advanced
S	Cherry Studio CherryHQ	Apps	Local	via Kimi K3	Free	beginner
S	LocalAI Ettore Di Giacinto (mudler)	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	exo EXO Labs	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	TextGen (text-generation-webui) oobabooga	Apps	Local	via Kimi K3	Free	intermediate
S	LibreChat LibreChat	Apps	Local	via Kimi K3	Free	advanced
S	Jan Menlo Research	Apps	Local	via Kimi K3	Free	beginner
S	Chatbox Chatbox AI	Apps	Local	via Kimi K3	Free tier · $3.99/mo	beginner
S	Khoj Khoj	Apps	Local	via Kimi K3	Free	intermediate
S	SGLang SGLang project (LMSYS)	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	KTransformers KVCache.AI (Tsinghua MADSys)	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	TensorRT LLM NVIDIA	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	Portkey AI Gateway Portkey	Runtimes & gateways	Local	via Kimi K3 Cloud models: tier S	Free	advanced
S	HuggingChat Hugging Face	Apps	Cloud	via Kimi K3	Free tier · $9/mo	beginner
S	Xinference Xorbits	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	LMDeploy InternLM (Shanghai AI Laboratory)	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	MLX LM Apple (ml-explore)	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	Big-AGI Big-AGI	Apps	Local	via Kimi K3	Free	intermediate
S	DeepChat ThinkInAI	Apps	Local	via Kimi K3	Free	beginner
S	GPUStack GPUStack	Runtimes & gateways	Local	via Kimi K3	Free	advanced
S	5ire nanbingxyz	Apps	Local	via Kimi K3	Free	beginner
S	Witsy Kochava Studios	Apps	Local	via Kimi K3	Free	beginner
S	Fireworks AI Fireworks AI	Runtimes & gateways	Cloud	via Kimi K3	—	intermediate
S	Hugging Face Inference Providers Hugging Face	Runtimes & gateways	Cloud	via Kimi K3	Free tier · $9/mo	intermediate
S	Kagi Assistant Kagi	Apps	Cloud	via Gemini 3.1 Pro (Preview)	Free tier · $5/mo	beginner
S	Kimi Moonshot AI	Apps	Cloud	via Kimi K3	Free tier	beginner
S	LM Studio Element Labs	Apps	Local	via Kimi K3	Free	beginner
S	Msty Studio Msty	Apps	Local	via Kimi K3	Free	beginner
S	Novita AI Novita AI	Runtimes & gateways	Cloud	via Kimi K3	—	intermediate
S	Together AI Together AI	Runtimes & gateways	Cloud	via Kimi K3	—	intermediate
S	ChatGPT OpenAI	Apps	Cloud	via GPT-6.1 Sol	Free tier · $20/mo	beginner
S	Microsoft Copilot Microsoft	Apps	Cloud	via GPT-6.1 Sol	Free tier · $9.99/mo	beginner
A	Qwen3.8-Max Alibaba (Qwen)	Models	Cloud	1,482 on LMArena Text Arena (overall, style control)	$3/M tokens	—
A	MiMo-V2.6-Pro Xiaomi	Models	Local	1,479 on LMArena Text Arena (overall, style control)	~585 GB VRAM	—
A	GLM-5.3 Z.ai	Models	Local	1,479 on LMArena Text Arena (overall, style control)	~425 GB VRAM	—
A	GPT-6 Astra OpenAI	Models	Cloud	1,477 on LMArena Text Arena (overall, style control)	$20/M tokens	—
A	Claude Sonnet 5.5 Anthropic	Models	Cloud	1,475 on LMArena Text Arena (overall, style control)	$4/M tokens	—
A	DeepSeek-V4.1-Flash-1017 DeepSeek	Models	Local	1,475 on LMArena Text Arena (overall, style control)	~320 GB VRAM	—
A	GLM-5.3-Flash Z.ai	Models	Local	1,474 on LMArena Text Arena (overall, style control)	~185 GB VRAM	—
A	ERNIE 5.1 Baidu	Models	Cloud	1,467 on LMArena Text Arena (overall, style control)	—	—
A	DeepSeek-V4-Pro-0813 DeepSeek	Models	Local	1,465 on LMArena Text Arena (overall, style control)	~920 GB VRAM	—
A	Qwen3.7-Plus Alibaba (Qwen)	Models	Cloud	1,456 on LMArena Text Arena (overall, style control)	$0.56/M tokens	—
A	Gemini 3.5 Flash-Lite Google	Models	Cloud	1,455 on LMArena Text Arena (overall, style control)	$0.85/M tokens	—
A	Gemma 4 (31B) Google DeepMind	Models	Local	1,452 on LMArena Text Arena (overall, style control)	~19 GB VRAM	—
A	MiMo-V2.6-Flash Xiaomi	Models	Local	1,451 on LMArena Text Arena (overall, style control)	~178 GB VRAM	—
A	Step 5 Preview StepFun	Models	Local	1,447 on LMArena Text Arena (overall, style control)	~346 GB VRAM	—
A	Grok 4.7 xAI	Models	Cloud	1,444 on LMArena Text Arena (overall, style control)	$3/M tokens	—
A	GPT-6 Luna OpenAI	Models	Cloud	1,443 on LMArena Text Arena (overall, style control)	$0.2/M tokens	—
A	MiniMax-M3 MiniMax	Models	Local	1,441 on LMArena Text Arena (overall, style control)	~245 GB VRAM	—
A	Inkling Thinking Machines Lab	Models	Local	1,441 on LMArena Text Arena (overall, style control)	~557 GB VRAM	—
A	Qwen3.8-27B Alibaba (Qwen)	Models	Local	1,438 on LMArena Text Arena (overall, style control)	~17 GB VRAM	—
A	Mistral Large 4 (preview) Mistral AI	Models	Cloud	1,432 on LMArena Text Arena (overall, style control)	$2.06/M tokens	—
A	Mistral Medium 3.5 Mistral AI	Models	Local	1,426 on LMArena Text Arena (overall, style control)	~75 GB VRAM	—
A	Nemotron 3 Ultra 550B-A55B NVIDIA	Models	Local	1,426 on LMArena Text Arena (overall, style control)	~321 GB VRAM	—
A	Muse Glimmer 30B Meta	Models	Local	1,425 on LMArena Text Arena (overall, style control)	~19 GB VRAM	—
A	Cloudflare Workers AI Cloudflare	Runtimes & gateways	Cloud	via GLM-5.3	Free tier	advanced
A	NVIDIA NIM APIs (build.nvidia.com) NVIDIA	Runtimes & gateways	Cloud	via GLM-5.3	Free tier	intermediate
A	Unsloth (Studio / Desktop app) Unsloth AI	Apps	Local	via DeepSeek-V4.1-Flash-1017	Free	intermediate
A	llamafile Mozilla.ai	Runtimes & gateways	Local	via GLM-5.3-Flash	Free	intermediate
A	LLM (CLI) Simon Willison	Runtimes & gateways	Local	via GLM-5.3-Flash Cloud models: tier S	Free	advanced
A	AIChat sigoden	Runtimes & gateways	Local	via GLM-5.3-Flash	Free	advanced
A	Page Assist n4ze3m	Apps	Local	via GLM-5.3-Flash	Free	beginner
A	Osaurus Osaurus	Apps	Local	via GLM-5.3-Flash	Free	intermediate
A	mistral.rs Eric Buehler	Runtimes & gateways	Local	via GLM-5.3-Flash	Free	advanced
A	Enchanted gluonfield	Apps	Local	via GLM-5.3-Flash	Free	intermediate
A	llama-swap mostlygeek	Runtimes & gateways	Local	via GLM-5.3-Flash	Free	advanced
A	Lemonade AMD (lemonade-sdk)	Runtimes & gateways	Local	via GLM-5.3-Flash	Free	intermediate
A	RamaLama RamaLama project (containers)	Runtimes & gateways	Local	via GLM-5.3-Flash	Free	advanced
A	Alpaca Jeffser	Apps	Local	via GLM-5.3-Flash	Free	beginner
A	TabbyAPI (ExLlamaV3) theroyallab	Runtimes & gateways	Local	via GLM-5.3-Flash	Free	advanced
A	Docker Model Runner Docker	Runtimes & gateways	Local	via GLM-5.3-Flash	Free	intermediate
A	BoltAI BoltAI	Apps	Local	via GLM-5.3-Flash Cloud models: tier S	—	beginner
A	TypingMind TypingMind	Apps	Local	via GLM-5.3-Flash Cloud models: tier S	—	intermediate
A	Z.ai Chat Z.ai	Apps	Cloud	via GLM-5.3-Flash	—	beginner
A	Wenxin Assistant (ERNIE Bot) Baidu	Apps	Cloud	via ERNIE 5.1	—	beginner
A	DeepSeek DeepSeek	Apps	Cloud	via DeepSeek-V4-Pro-0813	Free	beginner
A	Yuanbao Tencent	Apps	Cloud	via DeepSeek-V4-Pro-0813	Free	beginner
A	Google AI Edge Gallery Google	Apps	Local	via Gemma 4 (31B)	Free	beginner
A	MLC LLM MLC AI	Runtimes & gateways	Local	via Gemma 4 (31B)	Free	advanced
A	WebLLM MLC AI	Runtimes & gateways	Local	via Gemma 4 (31B)	Free	advanced
A	PocketPal AI a-ghorbani	Apps	Local	via Gemma 4 (31B)	Free	beginner
A	GenieX Qualcomm	Runtimes & gateways	Local	via Gemma 4 (31B)	Free	advanced
A	ChatterUI Vali-98	Apps	Local	via Gemma 4 (31B)	Free	intermediate
A	Maid Mobile Artificial Intelligence	Apps	Local	via Gemma 4 (31B)	Free	intermediate
A	Llama ggml-org and Hugging Face	Apps	Local	via Gemma 4 (31B)	Free	beginner
A	Duck.ai DuckDuckGo	Apps	Cloud	via Gemma 4 (31B)	Free tier	beginner
A	Locally AI Element Labs (LM Studio)	Apps	Local	via Gemma 4 (31B)	—	beginner
A	SambaNova Cloud SambaNova	Runtimes & gateways	Cloud	via Gemma 4 (31B)	—	intermediate
A	Grok SpaceXSI (formerly xAI)	Apps	Cloud	via Grok 4.7	Free tier · $8/mo	beginner
A	Cerebras Inference Cerebras	Runtimes & gateways	Cloud	via Qwen3.8-27B	Free tier	intermediate
A	Groq Groq	Runtimes & gateways	Cloud	via Qwen3.8-27B	—	intermediate
A	Vibe (formerly Le Chat) Mistral AI	Apps	Cloud	via Mistral Medium 3.5	Free tier · $15/mo	beginner
B	Nemotron 3.5 Super VL 120B-A12B NVIDIA	Models	Local	1,416 on LMArena Text Arena (overall, style control)	~72 GB VRAM	—
B	Inkling Small Thinking Machines Lab	Models	Local	1,404 on LMArena Text Arena (overall, style control)	~159 GB VRAM	—
B	Solar Pro 4 Upstage	Models	Cloud	1,386 on LMArena Text Arena (overall, style control)	$0.52/M tokens	—
B	Claude Haiku 5.5 Anthropic	Models	Cloud	43 on Artificial Analysis Intelligence Index	$0.2/M tokens	—
B	Trinity Large Thinking Arcee AI	Models	Local	1,367 on LMArena Text Arena (overall, style control)	~229 GB VRAM	—
B	Ling-3.1-flash inclusionAI (Ant Group)	Models	Local	41 on Artificial Analysis Intelligence Index	~321 GB VRAM	—
B	gpt-oss-120b OpenAI	Models	Local	1,352 on LMArena Text Arena (overall, style control)	~80 GB VRAM	—
B	Nemotron 3.5 Lightning 30B-A3B NVIDIA	Models	Local	1,351 on LMArena Text Arena (overall, style control)	~20 GB VRAM	—
B	Qwen3.8-2.4T-A95B Alibaba (Qwen)	Models	Local	40 on Artificial Analysis Intelligence Index	~1370 GB VRAM	—
B	Qwen3.8-Flash-Next Alibaba (Qwen)	Models	Local	40 on Artificial Analysis Intelligence Index	~104 GB VRAM	—
B	Qwen Chat Alibaba (Qwen team)	Apps	Cloud	via Qwen3.8-2.4T-A95B	Free	beginner
C	Granite 4.2 30B IBM	Models	Local	1,340 on LMArena Text Arena (overall, style control)	~18 GB VRAM	—
C	Muse Spark Open (816B-A42B) Meta	Models	Local	39 on Artificial Analysis Intelligence Index	~470 GB VRAM	—
C	Olmo 3.1 32B Allen Institute for AI (Ai2)	Models	Local	1,329 on LMArena Text Arena (overall, style control)	~20 GB VRAM	—
C	Llama 4 Maverick Meta	Models	Local	1,327 on LMArena Text Arena (overall, style control)	~230 GB VRAM	—
C	gpt-oss-20b OpenAI	Models	Local	1,317 on LMArena Text Arena (overall, style control)	~16 GB VRAM	—
C	Motif-3 Motif Technologies	Models	Local	34 on Artificial Analysis Intelligence Index	~181 GB VRAM	—
C	K2-Horizon-375B-A23B MBZUAI Institute of Foundation Models	Models	Local	31 on Artificial Analysis Intelligence Index	~218 GB VRAM	—
C	Beam 1.0 (501B-A23B) Reflection AI	Models	Local	30 on Artificial Analysis Intelligence Index	~287 GB VRAM	—
C	Kimi K2.7 Code Moonshot AI	Models	Local	26 on Artificial Analysis Intelligence Index	~587 GB VRAM	—
C	K2-Horizon-MoVA-36B-A4B MBZUAI Institute of Foundation Models	Models	Local	25 on Artificial Analysis Intelligence Index	~23 GB VRAM	—
C	Solar Open2 250B Upstage	Models	Local	25 on Artificial Analysis Intelligence Index	~144 GB VRAM	—
C	A.X K2 SK Telecom	Models	Local	21 on Artificial Analysis Intelligence Index	~396 GB VRAM	—
C	Nemotron 3.5 Bolt 74B-A9B NVIDIA	Models	Local	21 on Artificial Analysis Intelligence Index	~24 GB VRAM	—
C	K-EXAONE 2.0 (750B-A37B) LG AI Research	Models	Local	20 on Artificial Analysis Intelligence Index	~428 GB VRAM	—
C	LongCat-2.0 Meituan (LongCat)	Models	Local	19 on Artificial Analysis Intelligence Index	~1014 GB VRAM	—
C	Command A+ (05-2026) Cohere	Models	Local	13 on Artificial Analysis Intelligence Index	~126 GB VRAM	—
C	Mercury 2.5 Inception	Models	Cloud	12 on Artificial Analysis Intelligence Index	$0.34/M tokens	—
C	Ministral 3 14B (2512) Mistral AI	Models	Local	6 on Artificial Analysis Intelligence Index	~9 GB VRAM	—
C	Mistral Small 4 (2603) Mistral AI	Models	Local	11 on Artificial Analysis Intelligence Index	~69 GB VRAM	—
C	Ring-2.6-1T inclusionAI (Ant Group)	Models	Local	17 on Artificial Analysis Intelligence Index	~586 GB VRAM	—
C	Sarvam-105B Sarvam AI	Models	Local	9 on Artificial Analysis Intelligence Index	~62 GB VRAM	—
C	Foundry Local Microsoft	Runtimes & gateways	Local	via gpt-oss-20b	Free	intermediate
–	Alexa+ Amazon	Apps	Cloud	No public result yet	Free tier · $20/mo	beginner
–	Brave Leo Brave	Apps	Local	No public result yet	Free tier · $15/mo	beginner
–	Doubao ByteDance	Apps	Cloud	No public result yet	Free tier	beginner
–	Hy4-preview Tencent	Models	Local	No public result yet	~441 GB VRAM	—
–	iFlytek Spark (Xinghuo) iFlytek	Apps	Cloud	No public result yet	—	beginner
–	Laguna M.1 Poolside	Models	Local	No public result yet	~130 GB VRAM	—
–	LFM2.5-24B-A2B Liquid AI	Models	Local	No public result yet	~15 GB VRAM	—
–	Lumo Proton	Apps	Cloud	No public result yet	Free tier · $13/mo	beginner
–	Monica Monica	Apps	Cloud	No public result yet	—	beginner
–	Seed 2.1 Pro ByteDance Seed	Models	Cloud	No public result yet	—	—

Benchmarks used

LMArena Text Arena (overall, style control) by LMArena (arena.ai) (blind human votes, Arena score (Bradley-Terry rating from pairwise human votes, style-controlled default view)) · snapshot 15 Oct 2026
Read from LMArena's official Hugging Face dataset lmarena-ai/leaderboard-dataset (text_style_control, latest split, category overall, publish date 2026-10-15) because arena.ai blocks automated fetches. Covers all current closed frontier models except Claude Haiku 5.5, and most open-weights families; Muse Spark Open, Qwen3.8-2.4T-A95B, Qwen3-Coder-Next and Devstral are not listed. Several new entries have few votes (e.g. #1 Gemini 4 Argon ~4.9k votes, CI ±9).
Artificial Analysis Intelligence Index by Artificial Analysis (automated tests, Composite index over Artificial Analysis' own evaluation suite) · snapshot 19 Oct 2026
Values taken from the model data embedded in the leaderboard page (the page shows rounded integers and states 135 models ranked (68 open weights); no last-updated date shown). Covers nearly all current closed and open families; Devstral is absent. Older versions score much lower than on earlier index versions, so compare only within this snapshot. Some entries are flagged 'estimated' by AA; non-estimated entries were preferred.

Chat & assistants

Quality vs. price

Quality vs. setup

Everything, in order

Benchmarks used