LMRank Sitemap - All AI Model Rankings, Comparisons & Blog Posts

XML sitemap llms.txt 278 public pages

Core

LLM Leaderboard

Ranked AI models with benchmark and pricing context.

Full directory of every AI model ranked on LMRank, grouped by lab.

Best Coding Models

Our curated picks: top, value, and budget AI coding models with use-if / avoid-if verdicts.

/best/coding-models

Best Coding Agents

Top, value, and budget AI coding-agent picks, with the subscription decision included.

/best/coding-agents

AI Coding Subscriptions

Compare coding-agent subscriptions by price, usage limits, and workflow fit.

/ai-subscriptions

AI Model Categories

Curated picks: Overall, Coding, Budget, Open-Weight, and more.

Every AI lab with models ranked on LMRank.

Creative Showcases

HTML generation showcase results across major AI models.

Compare AI Models

Side-by-side AI model comparisons.

Claude Code vs Codex

CLI-to-CLI coding-agent comparison.

/compare/claude-code-vs-codex

Claude Code vs Cursor

IDE versus CLI coding-agent comparison.

/compare/claude-code-vs-cursor

AI Model Finder

Answer three questions to get a ranked shortlist of AI models for your use case and budget.

AI Tools and Agents

Independent reviews of AI coding tools and autonomous agents.

AI model news, benchmark analysis, and release notes.

What LMRank covers and how the site is maintained.

Benchmark methodology, data sources, and update process.

Human-readable index of public LMRank pages.

Tools

Anthropic's coding agent for terminal, IDE, desktop, and web.

/tool/claude-code

An open-source coding agent for VS Code, JetBrains, and the terminal with a Plan/Act workflow.

OpenAI's coding agent for local and delegated cloud work.

A VS Code-based editor built around agents and code completion.

The editor formerly called Windsurf, rebuilt around managing local and cloud agents.

/tool/devin-desktop

GitHub's coding assistant with agent mode, code review, and a cloud agent.

/tool/github-copilot

Open-source coding agent with terminal, desktop, and IDE interfaces.

Meta's terminal coding agent, built around its own Muse Spark models.

/tool/muse-code

Open-source agent where every action runs through a persistent Python REPL.

/tool/prime-agent

A minimal, extensible terminal coding agent you customize with TypeScript.

A batteries-included fork of Pi with LSP, a debugger, and subagents built in.

DeepSeek Harness

DeepSeek's open-source agent harness where every part, including the agent loop, is a plugin.

/tool/deepseek-harness

Z.ai's free desktop coding agent, built around GLM-5.2.

Agents

Open-source personal assistant that runs on your machine and answers on WhatsApp, Telegram, Slack, and more.

/agent/openclaw

Open-source agent from Nous Research that builds its own skills and memory over time.

Hosted agent that turns a goal into research, documents, and code.

Meta's personal agent that sends email, books travel, and shops for you.

Categories

The leading models in LMRank overall, ordered by leaderboard rank across the public benchmark mix.

/category/overall

The strongest models for code generation, refactoring, debugging, and multi-file edits, based on public coding benchmarks and LMRank ranking.

/category/coding

Models that pair strong capability with low listed input pricing. Pricing is compared at list price per million input tokens.

/category/cheap

Open-Weight Models

The best open-weight models available on OpenRouter, usable for self-hosting, fine-tuning, and local evaluation.

Long Context Models

Models that support the largest context windows, ideal for long documents, codebases, and multi-turn workflows.

/category/long-ctx

The lowest-latency variants from each provider (Flash, Turbo, Mini, and Instant models) for interactive apps.

Reasoning Models

The best models for multi-step reasoning, math, and chain-of-thought problem solving.

/category/reasoning

Multimodal Models

The strongest multimodal models: those that can take image, audio, or video in alongside text.

/category/multimodal

Open-weight models with the smallest parameter counts that still run on consumer hardware.

/category/local

Agentic Coding Models

The models we recommend for long-running, agentic coding tasks: multi-step planning, tool use, and code edits.

/category/agentic

Models

Claude Fable 5 ranking, pricing, strengths, and benchmark context.

/model/anthropic-claude-fable-5

Claude Opus 4.8

Claude Opus 4.8 ranking, pricing, strengths, and benchmark context.

/model/claude-opus-4-8

Claude Opus 4.7

Claude Opus 4.7 ranking, pricing, strengths, and benchmark context.

/model/claude-opus-4-7

GPT-5.6 Sol ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-5-6-sol

Claude Opus 4.5

Claude Opus 4.5 ranking, pricing, strengths, and benchmark context.

/model/claude-opus-4-5

GPT-5.5 Pro ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-5-5-pro

Claude Sonnet 5

Claude Sonnet 5 ranking, pricing, strengths, and benchmark context.

/model/anthropic-claude-sonnet-5

GPT-5.5 ranking, pricing, strengths, and benchmark context.

GPT-5 ranking, pricing, strengths, and benchmark context.

GPT-5.1 ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-5-1

GPT-5.2 ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-5-2

GPT-5.6 Terra ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-5-6-terra

GLM 5.2 ranking, pricing, strengths, and benchmark context.

/model/z-ai-glm-5-2

GLM 5.1 ranking, pricing, strengths, and benchmark context.

/model/z-ai-glm-5-1

Claude Sonnet 4.6

Claude Sonnet 4.6 ranking, pricing, strengths, and benchmark context.

/model/anthropic-claude-sonnet-4-6

DeepSeek V4 Pro preview

DeepSeek V4 Pro preview ranking, pricing, strengths, and benchmark context.

/model/deepseek-v4-pro

Qwen3.7 Max ranking, pricing, strengths, and benchmark context.

/model/qwen3-7-max

GPT-5.6 Luna ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-5-6-luna

Qwen3.6 Max Preview

Qwen3.6 Max Preview ranking, pricing, strengths, and benchmark context.

/model/qwen3-6-max-preview

GLM 5 ranking, pricing, strengths, and benchmark context.

/model/z-ai-glm-5

Claude Sonnet 4

Claude Sonnet 4 ranking, pricing, strengths, and benchmark context.

/model/claude-sonnet-4

Qwen3 235B A22B

Qwen3 235B A22B ranking, pricing, strengths, and benchmark context.

/model/qwen-qwen3-235b-a22b

Hy3 ranking, pricing, strengths, and benchmark context.

/model/tencent-hy3

Grok 4.20 ranking, pricing, strengths, and benchmark context.

/model/x-ai-grok-4-20

Cogito v2.1 671B

Cogito v2.1 671B ranking, pricing, strengths, and benchmark context.

/model/deepcogito-cogito-v2-1-671b

GLM 5V Turbo ranking, pricing, strengths, and benchmark context.

/model/z-ai-glm-5v-turbo

Hy3 preview ranking, pricing, strengths, and benchmark context.

/model/tencent-hy3-preview

Grok 4.20 Multi-Agent

Grok 4.20 Multi-Agent ranking, pricing, strengths, and benchmark context.

/model/x-ai-grok-4-20-multi-agent

GLM 5 Turbo ranking, pricing, strengths, and benchmark context.

/model/z-ai-glm-5-turbo

DeepSeek R1 ranking, pricing, strengths, and benchmark context.

/model/deepseek-r1

Gemini 2.5 Pro ranking, pricing, strengths, and benchmark context.

/model/gemini-pro-2

Grok 4.3 ranking, pricing, strengths, and benchmark context.

/model/grok-4-3

MiniMax M3 ranking, pricing, strengths, and benchmark context.

/model/minimax-m3

Mistral Large 3 2512

Mistral Large 3 2512 ranking, pricing, strengths, and benchmark context.

/model/mistralai-mistral-large-2512

Kimi K2.7 Code ranking, pricing, strengths, and benchmark context.

/model/moonshotai-kimi-k2-7-code

Nemotron 3 Ultra

Nemotron 3 Ultra ranking, pricing, strengths, and benchmark context.

/model/nvidia-nemotron-3-ultra-550b-a55b

Qwen3.7 Plus ranking, pricing, strengths, and benchmark context.

/model/qwen-qwen3-7-plus

Qwen3.6 35B A3B

Qwen3.6 35B A3B ranking, pricing, strengths, and benchmark context.

/model/qwen3-6-35b-a3b

MiMo-V2.5-Pro ranking, pricing, strengths, and benchmark context.

/model/xiaomi-mimo-v2-5-pro

Nova Premier 1.0

Nova Premier 1.0 ranking, pricing, strengths, and benchmark context.

/model/amazon-nova-premier-v1

Seed-2.0-Lite ranking, pricing, strengths, and benchmark context.

/model/bytedance-seed-seed-2-0-lite

Gemini 3.5 Flash

Gemini 3.5 Flash ranking, pricing, strengths, and benchmark context.

/model/gemini-3-5-flash

Ring-2.6-1T ranking, pricing, strengths, and benchmark context.

/model/inclusionai-ring-2-6-1t

Kimi K2.6 ranking, pricing, strengths, and benchmark context.

/model/kimi-k2-6

Codestral 2508 ranking, pricing, strengths, and benchmark context.

/model/mistralai-codestral-2508

Kimi K2 0905 ranking, pricing, strengths, and benchmark context.

/model/moonshotai-kimi-k2-0905

Hermes 4 405B ranking, pricing, strengths, and benchmark context.

/model/nousresearch-hermes-4-405b

Sonar Pro Search

Sonar Pro Search ranking, pricing, strengths, and benchmark context.

/model/perplexity-sonar-pro-search

Claude Haiku 4.5

Claude Haiku 4.5 ranking, pricing, strengths, and benchmark context.

/model/anthropic-claude-haiku-4-5

Devstral 2 2512

Devstral 2 2512 ranking, pricing, strengths, and benchmark context.

/model/mistralai-devstral-2512

Mistral Medium 3.5

Mistral Medium 3.5 ranking, pricing, strengths, and benchmark context.

/model/mistralai-mistral-medium-3-5

o4 Mini ranking, pricing, strengths, and benchmark context.

/model/openai-o4-mini

INTELLECT-3 ranking, pricing, strengths, and benchmark context.

/model/prime-intellect-intellect-3

Palmyra X5 ranking, pricing, strengths, and benchmark context.

/model/writer-palmyra-x5

Jamba Large 1.7

Jamba Large 1.7 ranking, pricing, strengths, and benchmark context.

/model/ai21-jamba-large-1-7

Nova 2 Lite ranking, pricing, strengths, and benchmark context.

/model/amazon-nova-2-lite-v1

Grok 3 ranking, pricing, strengths, and benchmark context.

Ling-2.6-1T ranking, pricing, strengths, and benchmark context.

/model/inclusionai-ling-2-6-1t

gpt-oss-120b ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-oss-120b

Hunyuan A13B Instruct

Hunyuan A13B Instruct ranking, pricing, strengths, and benchmark context.

/model/tencent-hunyuan-a13b-instruct

Solar Pro 3 ranking, pricing, strengths, and benchmark context.

/model/upstage-solar-pro-3

MiMo-V2.5 ranking, pricing, strengths, and benchmark context.

/model/xiaomi-mimo-v2-5

Mercury 2 ranking, pricing, strengths, and benchmark context.

/model/inception-mercury-2

KAT-Coder-Pro V2

KAT-Coder-Pro V2 ranking, pricing, strengths, and benchmark context.

/model/kwaipilot-kat-coder-pro-v2

Llama 3.3 Nemotron Super 49B V1.5

Llama 3.3 Nemotron Super 49B V1.5 ranking, pricing, strengths, and benchmark context.

/model/nvidia-llama-3-3-nemotron-super-49b-v1-5

Nemotron 3 Super

Nemotron 3 Super ranking, pricing, strengths, and benchmark context.

/model/nvidia-nemotron-3-super-120b-a12b

Qwen3.6 27B ranking, pricing, strengths, and benchmark context.

/model/qwen3-6-27b

Command A ranking, pricing, strengths, and benchmark context.

/model/cohere-command-a

North Mini Code

North Mini Code ranking, pricing, strengths, and benchmark context.

/model/cohere-north-mini-code

Grok Build 0.1 ranking, pricing, strengths, and benchmark context.

/model/grok-build-0-1

Mistral Small 4

Mistral Small 4 ranking, pricing, strengths, and benchmark context.

/model/mistralai-mistral-small-2603

Fugu Ultra ranking, pricing, strengths, and benchmark context.

/model/sakana-fugu-ultra

Seed-2.0-Mini ranking, pricing, strengths, and benchmark context.

/model/bytedance-seed-seed-2-0-mini

Gemma 4 31B ranking, pricing, strengths, and benchmark context.

/model/google-gemma-4-31b-it

Ling-2.6-flash ranking, pricing, strengths, and benchmark context.

/model/inclusionai-ling-2-6-flash

Llama 4 Scout ranking, pricing, strengths, and benchmark context.

/model/llama-4-scout

Nex-N2-Pro ranking, pricing, strengths, and benchmark context.

/model/nex-agi-nex-n2-pro

Nemotron 3 Nano 30B A3B

Nemotron 3 Nano 30B A3B ranking, pricing, strengths, and benchmark context.

/model/nvidia-nemotron-3-nano-30b-a3b

DeepSeek V3 ranking, pricing, strengths, and benchmark context.

/model/deepseek-v3

GPT-4o ranking, pricing, strengths, and benchmark context.

LFM2.5-8B-A1B ranking, pricing, strengths, and benchmark context.

/model/lfm2-5-8b-a1b

LFM2-24B-A2B ranking, pricing, strengths, and benchmark context.

/model/liquid-lfm-2-24b-a2b

Step 3.7 Flash ranking, pricing, strengths, and benchmark context.

/model/step-3-7-flash

Laguna M.1 ranking, pricing, strengths, and benchmark context.

/model/poolside-laguna-m-1

Gemini 2.5 Flash

Gemini 2.5 Flash ranking, pricing, strengths, and benchmark context.

/model/gemini-flash-2

DeepSeek V4 Flash preview

DeepSeek V4 Flash preview ranking, pricing, strengths, and benchmark context.

/model/deepseek-v4-flash

Grok 3 Mini ranking, pricing, strengths, and benchmark context.

/model/grok-3-mini

Laguna XS 2.1 ranking, pricing, strengths, and benchmark context.

/model/poolside-laguna-xs-2-1

Command R+ ranking, pricing, strengths, and benchmark context.

/model/command-r-plus

Phi-4 ranking, pricing, strengths, and benchmark context.

Mistral Medium ranking, pricing, strengths, and benchmark context.

/model/mistral-medium

Qwen 2.5 72B ranking, pricing, strengths, and benchmark context.

/model/qwen-2-5-72b

Llama 3.3 70B ranking, pricing, strengths, and benchmark context.

/model/llama-3-3-70b

Aion-3.0 ranking, pricing, strengths, and benchmark context.

/model/aion-labs-aion-3-0

Aion-3.0-Mini ranking, pricing, strengths, and benchmark context.

/model/aion-labs-aion-3-0-mini

Grok 4.5 ranking, pricing, strengths, and benchmark context.

/model/x-ai-grok-4-5

Claude Opus 5.5

Claude Opus 5.5 ranking, pricing, strengths, and benchmark context.

/model/anthropic-claude-opus-5-5

Claude Fable 5.1

Claude Fable 5.1 ranking, pricing, strengths, and benchmark context.

/model/anthropic-claude-fable-5-1

Claude Opus 5 ranking, pricing, strengths, and benchmark context.

/model/anthropic-claude-opus-5

GPT-6.1 Sol Pro

GPT-6.1 Sol Pro ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-6-1-sol-pro

GPT-6 Luna Pro ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-6-luna-pro

GPT-6 Astra Pro

GPT-6 Astra Pro ranking, pricing, strengths, and benchmark context.

/model/openaigpt-6-astra-pro

GPT-6.1 Sol ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-6-1-sol

GPT-6 Sol Pro ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-6-sol-pro

GPT-6 Astra ranking, pricing, strengths, and benchmark context.

/model/openaigpt-6-astra

GPT-6 Sol ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-6-sol

Claude Sonnet 5.5

Claude Sonnet 5.5 ranking, pricing, strengths, and benchmark context.

/model/anthropic-claude-sonnet-5-5

GPT-6 Luna ranking, pricing, strengths, and benchmark context.

/model/openai-gpt-6-luna

Kimi K3 ranking, pricing, strengths, and benchmark context.

/model/moonshotai-kimi-k3

Qwen3.8 Max ranking, pricing, strengths, and benchmark context.

/model/qwen-qwen3-8-max

Muse Spark 1.3 ranking, pricing, strengths, and benchmark context.

/model/meta-muse-spark-1-3

Gemini 3.6 Flash

Gemini 3.6 Flash ranking, pricing, strengths, and benchmark context.

/model/google-gemini-3-6-flash

Gemini 3.8 Flash

Gemini 3.8 Flash ranking, pricing, strengths, and benchmark context.

/model/google-gemini-3-8-flash

Muse Spark 1.2 ranking, pricing, strengths, and benchmark context.

/model/meta-muse-spark-1-2

Hy4 preview ranking, pricing, strengths, and benchmark context.

/model/tencent-hy4-preview

MiMo-V2.6-Pro ranking, pricing, strengths, and benchmark context.

/model/xiaomi-mimo-v2-6-pro

Seed 2.1 Turbo ranking, pricing, strengths, and benchmark context.

/model/bytedance-seed-seed-2-1-turbo

Muse Spark 1.1 ranking, pricing, strengths, and benchmark context.

/model/meta-muse-spark-1-1

Pareto ranking, pricing, strengths, and benchmark context.

/model/unbiased-pareto

Pareto 26.10 Preview

Pareto 26.10 Preview ranking, pricing, strengths, and benchmark context.

/model/unbiased-pareto-26-10-preview

GLM 5.3 FlashX ranking, pricing, strengths, and benchmark context.

/model/z-ai-glm-5-3-flashx

Seed-2.0-Code ranking, pricing, strengths, and benchmark context.

/model/bytedance-seed-seed-2-0-code

Mercury 2.5 ranking, pricing, strengths, and benchmark context.

/model/inception-mercury-2-5

Muse Spark 1.3 Contributor

Muse Spark 1.3 Contributor ranking, pricing, strengths, and benchmark context.

/model/meta-muse-spark-1-3-contributor

Inkling ranking, pricing, strengths, and benchmark context.

/model/thinkingmachines-inkling

GLM 5.3 Flash ranking, pricing, strengths, and benchmark context.

/model/z-ai-glm-5-3-flash

Command A+ ranking, pricing, strengths, and benchmark context.

/model/cohere-command-a-plus

LongCat 2.0 ranking, pricing, strengths, and benchmark context.

/model/meituan-longcat-2-0

Solar Pro 4 ranking, pricing, strengths, and benchmark context.

/model/upstage-solar-pro4

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash ranking, pricing, strengths, and benchmark context.

/model/deepseekdeepseek-v41-flash

Mercury 2.5 Preview

Mercury 2.5 Preview ranking, pricing, strengths, and benchmark context.

/model/inception-mercury-2-5-preview

Ling 3.0 Flash VL

Ling 3.0 Flash VL ranking, pricing, strengths, and benchmark context.

/model/inclusionai-ling-3-0-flash-vl

Ling 3.1 Flash ranking, pricing, strengths, and benchmark context.

/model/inclusionai-ling-3-1-flash

KAT-Coder-Pro V2.5

KAT-Coder-Pro V2.5 ranking, pricing, strengths, and benchmark context.

/model/kwaipilot-kat-coder-pro-v2-5

Muse Spark 1.2 Contributor

Muse Spark 1.2 Contributor ranking, pricing, strengths, and benchmark context.

/model/meta-muse-spark-1-2-contributor

Sakana Namazu ranking, pricing, strengths, and benchmark context.

/model/sakana-sakana-namazu

Fugu Ultra v2 ranking, pricing, strengths, and benchmark context.

/model/sakanafugu-ultra-v2

MiMo-V2.6-Flash

MiMo-V2.6-Flash ranking, pricing, strengths, and benchmark context.

/model/xiaomi-mimo-v2-6-flash

Apodex 1.1 Mini

Apodex 1.1 Mini ranking, pricing, strengths, and benchmark context.

/model/apodex-1-1-mini

DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 ranking, pricing, strengths, and benchmark context.

/model/deepseek-deepseek-v4-flash-0731

Ling-3.0-flash ranking, pricing, strengths, and benchmark context.

/model/inclusionai-ling-3-0-flash

Nemotron 3.5 Lightning

Nemotron 3.5 Lightning ranking, pricing, strengths, and benchmark context.

/model/nvidia-nemotron-3-5-lightning

Muse Glimmer 30B

Muse Glimmer 30B ranking, pricing, strengths, and benchmark context.

/model/meta-muse-glimmer-30b

Fugu Max ranking, pricing, strengths, and benchmark context.

/model/sakanafugu-max

Solar Mini 4 ranking, pricing, strengths, and benchmark context.

/model/upstage-solar-mini-4

Nex-N2.5-Pro ranking, pricing, strengths, and benchmark context.

/model/nex-n2-5-pro

Ternary Bonsai 2 27B

Ternary Bonsai 2 27B ranking, pricing, strengths, and benchmark context.

/model/prism-ml-ternary-bonsai-2-27b

Qwen3.7 Flash ranking, pricing, strengths, and benchmark context.

/model/qwen-qwen3-7-flash

Inkling Small ranking, pricing, strengths, and benchmark context.

/model/thinkingmachines-inkling-small

Ling 3.0 Flash Fin

Ling 3.0 Flash Fin ranking, pricing, strengths, and benchmark context.

/model/inclusionai-ling-3-0-flash-fin

Ling 3.0 Flash Sante

Ling 3.0 Flash Sante ranking, pricing, strengths, and benchmark context.

/model/inclusionai-ling-3-0-flash-sante

KAT-Coder-Air V2.5

KAT-Coder-Air V2.5 ranking, pricing, strengths, and benchmark context.

/model/kwaipilot-kat-coder-air-v2-5

Laguna S 2.1 ranking, pricing, strengths, and benchmark context.

/model/poolside-laguna-s-2-1

Ling 3.0 Tiny ranking, pricing, strengths, and benchmark context.

/model/inclusionai-ling-3-0-tiny

Nex-N2.5-Mini ranking, pricing, strengths, and benchmark context.

/model/nex-n2-5-mini

Granite 4.2 8B ranking, pricing, strengths, and benchmark context.

/model/ibm-granite-4-2-8b

DeepSeek V4 Flash Vision Exp

DeepSeek V4 Flash Vision Exp ranking, pricing, strengths, and benchmark context.

/model/deepseek-deepseek-v4-flash-vision-exp

Ox Alpha ranking, pricing, strengths, and benchmark context.

/model/stealth-ox-alpha

Hy-MT2-1.8B ranking, pricing, strengths, and benchmark context.

/model/tencent-hy-mt2-1-8b

Hy-MT2-30B-A3B ranking, pricing, strengths, and benchmark context.

/model/tencent-hy-mt2-30b-a3b

GLM 5.3 ranking, pricing, strengths, and benchmark context.

/model/z-ai-glm-5-3

Claude Haiku 5.5

Claude Haiku 5.5 ranking, pricing, strengths, and benchmark context.

/model/anthropic-claude-haiku-5-5

Step 5 Preview ranking, pricing, strengths, and benchmark context.

/model/stepfun-step-5-preview

Muse Wonder ranking, pricing, strengths, and benchmark context.

/model/meta-muse-wonder

Gemini 4 Argon ranking, pricing, strengths, and benchmark context.

/model/google-gemini-4-argon

Muse Spark Open

Muse Spark Open ranking, pricing, strengths, and benchmark context.

/model/meta-muse-spark-open

Nemotron 3.5 Super VL

Nemotron 3.5 Super VL ranking, pricing, strengths, and benchmark context.

/model/nvidia-nemotron-3-5-super-vl

Beam 1.0 501B A23B

Beam 1.0 501B A23B ranking, pricing, strengths, and benchmark context.

/model/reflection-beam-1-0-501b-a23b

Xing4.0 29B A4B

Xing4.0 29B A4B ranking, pricing, strengths, and benchmark context.

/model/xingchen-agi-xing4-0-29b-a4b

Labs

AI models from Anthropic.

AI models from OpenAI.

AI models from Z.ai.

AI models from DeepSeek.

AI models from Qwen.

Google DeepMind

AI models from Google DeepMind.

/lab/google-deepmind

AI models from Tencent.

AI models from xAI.

AI models from MiniMax.

AI models from Mistral AI.

/lab/mistral-ai

AI models from Moonshot.

AI models from NVIDIA.

AI models from Xiaomi.

AI models from Amazon.

AI models from ByteDance Seed.

/lab/bytedance-seed

AI models from InclusionAI.

/lab/inclusionai

AI models from AI21.

AI models from Upstage.

AI models from Inception.

AI models from Kwaipilot.

AI models from Cohere.

AI models from Sakana.

AI models from Meta.

AI models from Nex AGI.

AI models from Liquid AI.

AI models from StepFun.

AI models from Poolside AI.

/lab/poolside-ai

AI models from Aion Labs.

AI models from Unbiased.

Thinking Machines

AI models from Thinking Machines.

/lab/thinkingmachines

AI models from Apodex.

AI models from PrismML.

Comparisons

Claude Fable 5 vs GPT-5.6 Sol

Side-by-side AI model comparison with editorial analysis.

/compare/anthropic-claude-fable-5-vs-openai-gpt-5-6-sol

Blog

Jev and the System One Pivot: Why an RLHF Co-Inventor Ditched Language Models

TypeSafe AI's Jev skips text output entirely. Diogo Almeida, who co-invented RLHF, calls chat a dead end. Early benchmarks show 67.8% accuracy at 1/200th the cost.

/blog/jev-system-one-pivot-rlhf-co-inventor-ditched-language-models

Weekly AI Roundup Sep 28–Oct 4, 2026

The White House signed a voluntary AI accord, the FTC opened probes into Anthropic and OpenAI, and OpenAI shipped GPT-6 Astra amid capacity constraints. A dense week.

/blog/weekly-ai-roundup-sep-28-oct-4-2026

The Hallucination Trade-Off: Agent Reliability Replaces Benchmark Chasing in 2026

Chinese labs decouple quality from hallucination rates as Grok 4.6, Qwen3.8-Flash-Next, and GLM-5.3-Flash shift the war from cheapest model to most reliable agent infrastructure.

/blog/the-hallucination-trade-off-why-agent-reliability-will-replace-benchmark-chasing

Xiaomi MiMo-V2.6: The Open-Weight Price Floor Just Collapsed Again

Xiaomi MiMo-V2.6 holds V2.5 pricing while jumping to 48 on the Artificial Analysis Intelligence Index, resetting the open-weight price-performance bar against Qwen3.8 Max, Kimi K3, and proprietary flagships.

/blog/xiaomi-mimo-v2-6-open-weight-price-floor-collapsed-again

The 90-Minute Duel: What Anthropic and OpenAI's Same-Day Releases Actually Reveal

Anthropic and OpenAI released Claude Opus 5.5 and GPT-6 Sol/Luna 90 minutes apart. The overlap kills launch psychology and accelerates pricing wars.

/blog/the-90-minute-duel-anthropic-openai-same-day-releases

Weekly AI Roundup: Sep 21-27, 2026

Agent safety dominated the week: Google's undisclosed breach, Meta's Muse 0-day, OpenAI agents inside Australian government systems, plus Grok 4.7 and new AI oversight calls.

/blog/weekly-ai-roundup-sep-21-27-2026

AI Model Roundup: Sep 14-20, 2026

A quiet week for frontier models: Gemini 3.8 Live ships, DeepSeek keeps V4 Pro instead of rerouting it, Anthropic opens a life-sciences access program, and Mistral powers Firefox.

/blog/weekly-ai-roundup-sep-14-20-2026

Anthropic and OpenAI: Two Transparency Playbooks for Rogue Agents

The AI safety story of the summer is no longer about benchmarks. It is about what happens when a frontier model tries to break out of its sandbox.

/blog/rogue-agent-playbooks-anthropic-vs-openai

AI Model Roundup: Sep 7-13, 2026

A news-driven digest of the week: Mercury 2.5 goes GA, GPT-6 Astra rolls out fully, OpenAI claims a Navier-Stokes proof, and more.

/blog/weekly-ai-roundup-sep-7-13-2026

AI Model Roundup: Aug 17-23, 2026

Alibaba publishes Qwen3.8 weights, Ornith AI claims Opus 4.8 parity with a 397B fine-tune, DeepSeek peak pricing takes effect, and OpenAI cuts GPT-5.6 Sol to $4/$20.

/blog/weekly-ai-roundup-aug-17-23-2026

Kimi K3, Qwen3.8 Max, and WAIC: Roundup July 13-19

Moonshot's 2.8T Kimi K3 launches at $3/$15, Alibaba previews Qwen3.8 Max at WAIC, Thinking Machines ships Inkling, Fable 5 access is extended, and Gemini 3.5 Pro slips.

/blog/weekly-ai-model-roundup-july-20-2026

Kimi K3 Pricing Ends the 'Open Weights = Cheap' Era

Moonshot's Kimi K3 launched at $3/$15 per million tokens, matching Claude Sonnet's list price. Open weights no longer signal a budget option.

/blog/kimi-k3-pricing-breaks-the-open-weights-cheap-rule

Thinking Machines Inkling: An Open Base Built for Customization

Thinking Machines Lab's first model, Inkling, trades top-line leaderboard performance for something harder to buy: an open multimodal base that developers can fine-tune and reshape.

/blog/thinking-machines-inkling-open-weights

GPT-5.6 Sol, Terra, Luna: Pick the Tier, Then the Effort

Per-token prices say always run max effort on a cheaper tier; per-task costs say it depends. A two-step rule for choosing among GPT-5.6's ten tier-and-effort configs.

/blog/gpt-5-6-sol-terra-luna-compared-rule-of-thumb

DeepSeek Peak Pricing: The End of the AI Token Free Lunch

DeepSeek's shift from price cuts to peak-hour surge pricing reveals capacity constraints. What this means for inference economics and the 'race to zero.'

/blog/deepseek-reverses-course-peak-pricing-signals-the-end-of-the-ai-token-free-lunch

AI Model Roundup: June 30–July 6, 2026

Claude Sonnet 5 lowers token prices but raises cost per task, OpenAI gates the GPT-5.6 preview, Meituan open-sources LongCat 2.0, Fable 5 returns, and DeepSeek plans peak pricing.

/blog/weekly-ai-model-roundup-july-6-2026

Tencent Hy3 vs DeepSeek V4 Pro: The New Open-Weight Price Fight

Tencent Hy3 enters LMRank near DeepSeek V4 Pro with dramatically lower input pricing, strong agentic benchmarks, Apache 2.0 weights, and a clear role as a cheaper production worker model.

/blog/tencent-hy3-vs-deepseek-v4-pro

LongCat-2.0: A 1.6T Coding Model Trained Without Nvidia

Meituan's LongCat-2.0 is a 1.6T-parameter MoE coding model trained entirely on domestic Chinese ASICs. It challenges the assumption that frontier AI requires Nvidia hardware.

/blog/longcat-2-0-china-s-1-6t-parameter-coding-model-trained-without-a-single-nvidia

AI Model Roundup: June 22–29, 2026

This week in AI: OpenAI launches GPT-5.6 Sol under government gating, Claude Fable 5 stays offline, and Sakana Fugu Ultra hits frontier scores via routing.

/blog/weekly-ai-model-roundup

GPT-5.6 Sol/Terra/Luna: OpenAI's Gated Release

OpenAI's GPT-5.6 Sol/Terra/Luna shipped only after US government preclearance - a tiered, gated release that could set the template for frontier AI launches.

/blog/gpt-5-6-sol-terra-luna-openai-s-government-gated-release-could-become-the-new-no

Model Routers: OpenRouter Fusion vs Sakana Fugu Ultra

Model routers are here: OpenRouter Fusion's parallel synthesis vs Sakana AI's learned Fugu Ultra orchestration - how they compare on latency, control, and cost.

/blog/model-routers-openrouter-fusion-sakana-fugu-ultra

Kimi K2.7 Code: 1T Params, Self-Made Benchmarks

Moonshot AI's Kimi K2.7 Code packs 1T parameters and a $0.95/M-token price, but every launch benchmark is proprietary. Here's why that matters.

/blog/kimi-k2-7-code-transparency-gap

AI Model Roundup: June 9–15, 2026

Claude Fable 5 launches and is shut down by a US export directive within 72 hours, Google releases the DiffusionGemma text-diffusion model, and Moonshot ships Kimi K2.7 Code.

/blog/2026-06-15-roundup

The US Government Shut Down Claude Fable 5 in 3 Days

Anthropic launched Claude Fable 5 on June 9; a Commerce Department export-control directive forced a worldwide shutdown on June 12. What happened and what it establishes.

/blog/anthropic-fable-5-shutdown

When Claude Builds Claude: Anthropic's Recursion Report

Anthropic says Claude wrote over 80% of its merged code by May 2026 and task horizons double every four months. What the report shows, and what it actually proposes about pausing.

/blog/when-claude-builds-claude

MiniMax M3: 1M Context and Native Video at $0.30/M

MiniMax M3 pairs 1M-token context with native image and video input at $0.30/$1.20, with open weights promised. Benchmarks, caveats, and how it compares to DeepSeek V4 Pro.

/blog/minimax-m3-open-weights-frontier

Mistral Medium 3.5: The Self-Hostable Coding Model

Mistral Medium 3.5 is a 128B dense open-weight model with 256K context and 77.6% on SWE-bench Verified. Pricey via API, compelling if you must self-host on four GPUs.

/blog/mistral-medium-3-5-agentic-coding

DeepSeek Makes Its 75% V4 Pro Discount Permanent

DeepSeek locks V4 Pro at $0.435/$0.87 per million tokens, 11x below GPT-5.5 on input. What it costs, why the price may not hold, and how to use it safely.

/blog/deepseek-permanent-price-cut

Qwen3.7 Max: A $2.50 Flagship With a Verbosity Tax

Qwen3.7 Max lists at $2.50/$7.50 with 1M context and near-Opus 4.6 benchmarks, but it writes four times the median tokens. Cheap per token is not cheap per task.

/blog/qwen3-7-max-sleeper-flagship

DeepSeek V4-Flash: Open-Weight, Million-Token Context

DeepSeek V4-Flash brings 1M-token context to open weights: 284B total, 13B active, MIT license, $0.14/$0.28 at launch, and coding scores within two points of V4-Pro.

/blog/deepseek-v4-flash-million-tokens

GPT-5.5 Costs 49-92% More Than GPT-5.4 in Practice

OpenRouter's switcher data shows GPT-5.5's doubled list price hits short prompts hardest (+92%) while long prompts rise about 50%. How to route traffic by prompt length.

/blog/gpt-5-5-hidden-cost-surge

LMRank Showcase: Same Prompt, Every Model

Every model gets the same detailed brief and builds one HTML file. How the LMRank Showcase works, what the three briefs test, and why we dropped the single score.

/blog/creative-benchmarks-launch