Code & data

Write software and analyse data. 2 tasks, 209 listed options.

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

Coding

Write, review and ship code, from autocomplete to autonomous agents.

Best overallSClaude Opus 5.5
Best valueSClaude Sonnet 5.5
Best free startSWarp
Best local (≤24 GB GPU)CQwen3.8-27B

Models

Local

DeepSeek-V4.1-Flash-1017DeepSeek · ~320 GB VRAM$B

Kimi K3Moonshot AI · ~1600 GB VRAM B

Ling-3.1-flashinclusionAI (Ant Group) · ~321 GB VRAM B

MiMo-V2.6-FlashXiaomi · ~178 GB VRAM$B

Hy4-previewTencent · ~441 GB VRAM B

Qwen3.8-2.4T-A95BAlibaba (Qwen) · ~1370 GB VRAM B

Qwen3.8-Flash-NextAlibaba (Qwen) · ~104 GB VRAM$C

MiMo-V2.6-ProXiaomi · ~585 GB VRAM C

GLM-5.3Z.ai · ~425 GB VRAM C

GLM-5.3-FlashZ.ai · ~185 GB VRAM C

Qwen3.8-27BAlibaba (Qwen) · ~17 GB VRAM$C

DeepSeek-V4-Pro-0813DeepSeek · ~920 GB VRAM C

Motif-3Motif Technologies · ~181 GB VRAM C

Step 5 PreviewStepFun · ~346 GB VRAM C

K2-Horizon-375B-A23BMBZUAI Institute of Foundation Models · ~218 GB VRAM C

Muse Spark Open (816B-A42B)Meta · ~470 GB VRAM C

Nemotron 3.5 Super VL 120B-A12BNVIDIA · ~72 GB VRAM C

K2-Horizon-MoVA-36B-A4BMBZUAI Institute of Foundation Models · ~23 GB VRAM C

MiniMax-M3MiniMax · ~245 GB VRAM C

Solar Open2 250BUpstage · ~144 GB VRAM C

Kimi K2.7 CodeMoonshot AI · ~587 GB VRAM C

Nemotron 3 Ultra 550B-A55BNVIDIA · ~321 GB VRAM C

A.X K2SK Telecom · ~396 GB VRAM C

Nemotron 3.5 Bolt 74B-A9BNVIDIA · ~24 GB VRAM C

Beam 1.0 (501B-A23B)Reflection AI · ~287 GB VRAM C

K-EXAONE 2.0 (750B-A37B)LG AI Research · ~428 GB VRAM C

LongCat-2.0Meituan (LongCat) · ~1014 GB VRAM C

InklingThinking Machines Lab · ~557 GB VRAM C

Inkling SmallThinking Machines Lab · ~159 GB VRAM C

Command A+ (05-2026)Cohere · ~126 GB VRAM C

Devstral 2 (2512)Mistral AI · ~72 GB VRAM C

Gemma 4 (31B)Google DeepMind · ~19 GB VRAM C

gpt-oss-120bOpenAI · ~80 GB VRAM C

gpt-oss-20bOpenAI · ~16 GB VRAM$C

Granite 4.2 30BIBM · ~18 GB VRAM C

Laguna M.1Poolside · ~130 GB VRAM C

Llama 4 MaverickMeta · ~230 GB VRAM C

Mistral Medium 3.5Mistral AI · ~75 GB VRAM C

Mistral Small 4 (2603)Mistral AI · ~69 GB VRAM C

Muse Glimmer 30BMeta · ~19 GB VRAM C

Nemotron 3.5 Lightning 30B-A3BNVIDIA · ~20 GB VRAM C

North Mini Code 1.0Cohere · ~19 GB VRAM C

Qwen3-Coder-NextAlibaba (Qwen) · ~47 GB VRAM C

Ring-2.6-1TinclusionAI (Ant Group) · ~586 GB VRAM C

Trinity Large ThinkingArcee AI · ~229 GB VRAM –

Devstral Small 2 (2512)Mistral AI · ~15 GB VRAM –

Laguna XS 2.1Poolside · ~21 GB VRAM –

Mellum2.1 Thinking (12B-A2.5B)JetBrains · ~8 GB VRAM

Coding agents

Cloud

Claude CodeAnthropic · $20/mo S

Muse CodeMeta · $5/mo$S

WarpWarp · Free tier · $20/mo S

Abacus AI DesktopAbacus.AI · $10/mo$S

AmpAmp · Free tier · $20/mo S

CapyCapy Corporation · $20/mo S

DroidFactory · $20/mo A

CodexOpenAI · Free tier · $8/mo B

Grok BuildSpaceXAI (xAI) · Free tier · $8/mo B

Kimi CodeMoonshot AI C

Gemini CLIGoogle C

Freebuff (formerly Codebuff)Codebuff · Free$C

JulesGoogle · Free tier · $20/mo C

Vibe (formerly Le Chat)Mistral AI · Free tier · $15/mo –

Augment CodeAugment Code · $20/mo –

CodeRabbitCodeRabbit · Free tier · $30/mo –

GreptileGreptile · Free tier · $30/mo –

QodoQodo · $30/mo

Local

OpenCodeAnomaly Innovations · Free$B

gooseAgentic AI Foundation (AAIF); originally created by Block · Free$B AiderAider (open-source project, Aider-AI) · Free$B

Qwen CodeAlibaba (Qwen) · Free B

omp (oh-my-pi)Stencil Labs (can1357) · Free C

PiEarendil Inc. · Free C

OpenHandsOpenHands (All Hands AI) · Free –

Deep Agents CodeLangChain · Free –

CrushCharm · Free –

mini-swe-agentSWE-agent team (Princeton & Stanford) · Free –

NanocoderNano Collective · Free – Xum (formerly Mux)Coder · Free –

JunieJetBrains · Free tier · $8.33/mo

Editors & extensions

Cloud

Devin (Devin Desktop, formerly Windsurf)Cognition · Free tier · $20/mo S

CursorAnysphere (SpaceX/xAI) · Free tier · $8/mo$S GitHub CopilotGitHub (Microsoft) · Free tier · $10/mo S

KiroAmazon Web Services · Free tier · $20/mo S

TRAEByteDance · Free tier · $20/mo A

Google AntigravityGoogle · Free tier A

JetBrains AirJetBrains B

QoderAlibaba · Free tier · $20/mo – CodeBuddyTencent · Free tier · $10/mo

Local

ClineCline · Free$B

Kilo CodeKilo Code · Free$B

llama.vscodeggml-org · Free$–

ZedZed Industries · Free –

TabbyTabbyML · Free –

twinnytwinny · Free –

CodeGPTCodeGPT · Free tier · $10/mo

Runtimes & gateways

Cloud

Amazon BedrockAmazon Web Services S

DeepInfraDeepInfra S

Gemini Enterprise Agent Platform (formerly Vertex AI)Google Cloud S

OpenRouterOpenRouter · Free tier S

RequestyRequesty S

Vercel AI GatewayVercel · Free tier S

Microsoft FoundryMicrosoft B

Novita AINovita AI B

Hugging Face Inference ProvidersHugging Face · Free tier · $9/mo$B

NVIDIA NIM APIs (build.nvidia.com)NVIDIA · Free tier B

Together AITogether AI B

Fireworks AIFireworks AI C

Cloudflare Workers AICloudflare · Free tier C

Cerebras InferenceCerebras · Free tier C

SambaNova CloudSambaNova

Local

OllamaOllama · Free$B

llama.cppggml-org · Free$B

vLLMvLLM project · Free$B

Unsloth (Studio / Desktop app)Unsloth AI · Free$B

LiteLLMBerriAI · Free$B

LocalAIEttore Di Giacinto (mudler) · Free$B

exoEXO Labs · Free$B

TextGen (text-generation-webui)oobabooga · Free$B

SGLangSGLang project (LMSYS) · Free$B KTransformersKVCache.AI (Tsinghua MADSys) · Free$B

TensorRT LLMNVIDIA · Free$B

Portkey AI GatewayPortkey · Free$B

XinferenceXorbits · Free$B

MLX LMApple (ml-explore) · Free$B

GPUStackGPUStack · Free$B

LM StudioElement Labs · Free$B

LMDeployInternLM (Shanghai AI Laboratory) · Free C

llamafileMozilla.ai · Free C

LLM (CLI)Simon Willison · Free C

AIChatsigoden · Free C

OsaurusOsaurus · Free C

mistral.rsEric Buehler · Free C

llama-swapmostlygeek · Free C

LemonadeAMD (lemonade-sdk) · Free C

RamaLamaRamaLama project (containers) · Free C

TabbyAPI (ExLlamaV3)theroyallab · Free C

Docker Model RunnerDocker · Free C

MLC LLMMLC AI · Free C

WebLLMMLC AI · Free C GenieXQualcomm · Free C

Foundry LocalMicrosoft · Free

Full coding map, chart and table →

Data analysis

Ask questions of spreadsheets and data; get answers and charts.

Best overallBGemini 3.1 Pro (Preview)
Best valueNo qualifying option yet
Best free startAWPS Office (WPS AI)
Best local (≤24 GB GPU)No qualifying option yet

Models

Cloud

Gemini 3.1 Pro (Preview)Google · $4.5/M tokens$

Local

Nothing tracked yet

Apps

Cloud

WPS Office (WPS AI)Kingsoft Office · Free tier B

Gemini in Google WorkspaceGoogle B

GeminiGoogle · Free tier · $4.99/mo$C

Microsoft 365 CopilotMicrosoft · $25/mo C

ChatGPTOpenAI · Free tier · $20/mo C

ClaudeAnthropic · Free tier · $20/mo –

Better Analyst (formerly Formula Bot)Better Analyst · Free tier –

Databricks GenieDatabricks –

Gemini Notebook (formerly NotebookLM)Google · Free tier –

GPT for Work (becoming Autosheet)Talarian · Free tier · $25/mo –

HexHex · Free tier · $36/mo –

JuliusJulius AI –

Powerdrill BloomPowerdrill · Free tier · $17/mo –

QuadraticQuadratic · Free tier · $18/mo –

RowsRows (part of Superhuman) · Free tier · $8/mo –

Snowflake CoWorkSnowflake –

ThoughtSpotThoughtSpot · $25/mo

Local

Nothing tracked yet

Data agents & notebooks

Cloud

ShortcutShortcut · Free tier · $100/mo$–

DeepnoteDeepnote · Free tier –

DecideDecide AI · $7/mo –

Fabi.aiFabi.ai –

Google ColabGoogle · Free tier –

HexHex · Free tier · $36/mo

Local

marimomarimo · Free –

Jupyter AIProject Jupyter · Free

Full data analysis map, chart and table →