Leaderboard

    Best AI for Reasoning 2026.

    Find the best AI for reasoning. Ranked by Humanity's Last Exam, GPQA Diamond, ARC-AGI 2, SimpleQA, and more. Compare intelligence and reasoning across all major LLMs.

    LLMImageVideoSpeechTranscription
    Claude Opus 4.8
    Anthropic
    		0.6%0.9%——
    GLM-5.2OSS
    Z AI
    		0.5%0.9%——
    Claude Opus 4.7
    Anthropic
    		0.5%0.9%——
    Claude Opus 4.6
    Anthropic
    		0.5%0.9%—0.7%
    GLM-5.1OSS
    Z AI
    		0.5%0.9%——
    GPT-5.5
    OpenAI
    		0.5%0.9%—0.8%
    Gemini 3.1 Pro
    Google
    		0.5%0.9%—0.8%
    M
    Kimi K2-Thinking-0905OSS
    Moonshot AI
    		0.5%0.8%——
    M
    Kimi K2.5OSS
    Moonshot AI
    		0.5%0.9%——
    Claude Sonnet 4.6
    Anthropic
    		0.5%0.9%—0.6%
    Qwen3.5-27BOSS
    Qwen
    		0.5%0.9%——
    DeepSeek-V4-Pro-MaxOSS
    DeepSeek
    		0.5%0.9%0.6%—
    Qwen3.5-122B-A10BOSS
    Qwen
    		0.5%0.9%——
    Qwen3.5-35B-A3BOSS
    Qwen
    		0.5%0.8%——
    Gemini 3 Pro
    Google
    		0.5%0.9%0.7%0.3%
    DeepSeek-V4-Flash-MaxOSS
    DeepSeek
    		0.5%0.9%0.3%—
    Gemini 3 Flash
    Google
    		0.4%0.9%0.7%0.3%
    GLM-4.7OSS
    Z AI
    		0.4%0.9%——
    Qwen3.7 Max
    Qwen
    		0.4%0.9%——
    DeepSeek-V3.2OSS
    DeepSeek · via OpenRouter
    		0.4%0.8%——
    Gemini 3.5 Flash
    Google
    		0.4%——0.7%
    Grok-4
    xAI
    		0.4%0.9%—0.2%
    GPT-5.4
    OpenAI
    		0.4%0.9%—0.7%
    N
    Nemotron 3 Ultra (550B A55B)OSS
    NVIDIA · via OpenRouter
    		0.4%0.9%——
    GPT-5.2 Pro
    OpenAI
    		0.4%0.9%—0.5%
    M
    Kimi K2.6OSS
    Moonshot AI
    		0.4%0.9%——
    GPT-5.2
    OpenAI
    		0.3%0.9%—0.5%
    X
    MiMo-V2.5-ProOSS
    Xiaomi
    		0.3%0.7%——
    Qwen3.6 Plus
    Qwen
    		0.3%0.9%——
    Qwen3.5-397B-A17BOSS
    Qwen
    		0.3%0.9%——
    GPT-5.4 mini
    OpenAI
    		0.3%0.9%——
    Gemma 4 31BOSS
    Google
    		0.3%0.8%——
    M
    LongCat-Flash-Thinking-2601OSS
    Meituan
    		0.3%0.8%——
    GPT-5
    OpenAI
    		0.2%0.9%——
    GPT-5.4 nano
    OpenAI
    		0.2%0.8%——
    Qwen3.6-27BOSS
    Qwen
    		0.2%0.9%——
    N
    Nemotron 3 Super (120B A12B)OSS
    NVIDIA · via OpenRouter
    		0.2%0.8%——
    X
    MiMo-V2-FlashOSS
    Xiaomi
    		0.2%0.8%——
    M
    MiniMax M2.1OSS
    MiniMax
    		0.2%0.8%——
    Gemini 2.5 Pro Preview 06-05
    Google
    		0.2%0.9%0.5%—
    Qwen3.6-35B-A3BOSS
    Qwen · via OpenRouter
    		0.2%0.9%——
    Grok 4 Fast
    xAI
    		0.2%0.9%0.9%—
    DeepSeek-V3.2-ExpOSS
    DeepSeek
    		0.2%0.8%1.0%—
    Qwen3-235B-A22B-Thinking-2507OSS
    Qwen
    		0.2%0.8%——
    Gemini 2.5 Pro
    Google
    		0.2%0.8%0.5%0.0%
    DeepSeek-R1-0528OSS
    DeepSeek
    		0.2%0.8%0.9%—
    GLM-4.6OSS
    Z AI
    		0.2%0.8%——
    Gemma 4 26B-A4BOSS
    Google
    		0.2%0.8%——
    GPT-5 mini
    OpenAI
    		0.2%0.8%——
    Gemini 3.1 Flash-Lite
    Google
    		0.2%0.9%0.4%—
    Showing 1–50 of 236 models

    Building with these APIs?

    Get 10+ Next.js AI templates with auth, payments, and more.

    Get Templates — $249

    All Large Language Models

    OpenAI

    44 models
    GPT-5.5 Instant·GPT-5.5·GPT-5.4 mini·GPT-5.4 nano·GPT-5.4·GPT-5.3 Chat·GPT-5.3 Codex·GPT-5.2 Codex·GPT-5.2·GPT-5.2 Pro·GPT-5.1 Codex·GPT-5.1·GPT-5.1 Codex High·GPT-5.1 Codex Mini·GPT-5.1 High·GPT-5.1 Instant·GPT-5.1 Medium·GPT-5.1 Thinking·GPT-5·GPT-5 High·GPT-5 Medium·GPT-5 mini·GPT-5 nano·GPT OSS 120B·GPT OSS 120B High·GPT OSS 20B·GPT OSS 20B High·o3-pro·o3·o4-mini·GPT-4.1·GPT-4.1 mini·GPT-4.1 nano·o3-mini·o1·o1-mini·o1-preview·GPT-4o·GPT-4o mini·ChatGPT-4o Latest·GPT-4o·GPT-4 Turbo·GPT-4·GPT-3.5 Turbo

    Anthropic

    16 models
    Claude Opus 4.8·Claude Opus 4.7·Claude Sonnet 4.6·Claude Opus 4.6·Claude Opus 4.5·Claude Haiku 4.5·Claude Sonnet 4.5·Claude Opus 4.1·Claude Opus 4·Claude Sonnet 4·Claude 3.7 Sonnet·Claude 3.5 Haiku·Claude 3.5 Sonnet·Claude 3 Haiku·Claude 3 Opus·Claude 3 Sonnet

    Google

    22 models
    Gemini 3.5 Flash·Gemma 4 26B-A4B·Gemma 4 31B·Gemini 3.1 Flash-Lite·Gemini 3.1 Pro·Gemini 3 Flash·Gemini 3 Pro·Gemma 3n E4B Instructed·Gemini 2.5 Flash-Lite·Gemini 2.5 Pro Preview 06-05·Gemini 2.5 Flash·Gemini 2.5 Pro·Gemma 3 12B·Gemma 3 27B·Gemma 3 4B·Gemini 2.0 Flash-Lite·Gemini 2.0 Flash·Gemma 2 27B·Gemini 1.5 Flash·Gemini 1.5 Pro·Gemini 1.5 Flash 8B·Gemini 1.0 Pro

    xAI

    13 models
    Grok 4.3·Grok-4.1·Grok-4.1 Fast Non-Reasoning·Grok-4.1 Fast Reasoning·Grok-4.1 Thinking·Grok 4 Fast·Grok Code Fast 1·Grok-4 Fast Non-Reasoning·Grok-4 Fast Reasoning·Grok-4·Grok-3·Grok-3 Mini·Grok-2

    DeepSeek

    13 models
    DeepSeek-V4-Flash-Max·DeepSeek-V4-Pro-Max·DeepSeek-V3.2·DeepSeek-V3.2 (Non-thinking)·DeepSeek-V3.2-Exp·DeepSeek-R1-0528·DeepSeek-V3 0324·DeepSeek R1 Distill Llama 70B·DeepSeek R1 Distill Qwen 32B·DeepSeek-R1·DeepSeek-V3.1·DeepSeek-V3·DeepSeek-V2.5

    MiniMax

    6 models
    MiniMax M3·MiniMax M2.7·MiniMax M2.5·MiniMax M2.1·MiniMax M2·MiniMax M1 80K

    Qwen

    33 models
    Qwen3.7 Max·Qwen3.6-27B·Qwen3.6-35B-A3B·Qwen3.6 Plus·Qwen3.5-9B·Qwen3.5-122B-A10B·Qwen3.5-27B·Qwen3.5-35B-A3B·Qwen3.5-397B-A17B·Qwen3 Max·Qwen3 VL 235B A22B Instruct·Qwen3 VL 235B A22B Thinking·Qwen3 VL 30B A3B Instruct·Qwen3 VL 30B A3B Thinking·Qwen3 VL 32B Instruct·Qwen3 VL 4B Instruct·Qwen3 VL 4B Thinking·Qwen3 VL 8B Instruct·Qwen3 VL 8B Thinking·Qwen3-Next-80B-A3B-Instruct·Qwen3-Next-80B-A3B-Thinking·Qwen3-235B-A22B-Thinking-2507·Qwen3-235B-A22B-Instruct-2507·Qwen3 235B A22B·Qwen3 30B A3B·Qwen3 32B·Qwen3-Coder 480B A35B Instruct·Qwen2.5 VL 72B Instruct·Qwen3-Coder·QwQ-32B-Preview·Qwen2.5 72B Instruct·Qwen2.5 7B Instruct·Qwen2.5-Coder 32B Instruct

    AI21 Labs

    2 models
    Jamba 1.5 Large·Jamba 1.5 Mini

    Amazon

    5 models
    Nova 2 Lite·Nova 2 Sonic·Nova Lite·Nova Micro·Nova Pro

    Baidu

    1 models
    ERNIE 4.5

    Cohere

    2 models
    North Mini Code 1.0·Command R+

    IBM

    1 models
    Granite 3.3 8B Instruct

    Inception

    1 models
    Mercury 2

    LG AI Research

    1 models
    K-EXAONE-236B-A23B

    Meituan

    4 models
    LongCat-Flash-Lite·LongCat-Flash-Thinking-2601·LongCat-Flash-Thinking·LongCat-Flash-Chat

    Meta

    9 models
    Llama 4 Maverick·Llama 4 Scout·Llama 3.3 70B Instruct·Llama 3.2 11B Instruct·Llama 3.2 3B Instruct·Llama 3.2 90B Instruct·Llama 3.1 405B Instruct·Llama 3.1 70B Instruct·Llama 3.1 8B Instruct

    Microsoft

    4 models
    Phi 4 Mini·Phi-4-multimodal-instruct·Phi 4·Phi-3.5-mini-instruct

    Mistral AI

    22 models
    Mistral Medium 3.5·Mistral Small 4·Min istral 3 (3B Reasoning 2512)·MiniStral 3 (14B Instruct 2512)·Ministral 3 (14B Reasoning 2512)·Ministral 3 (3B Instruct 2512)·Ministral 3 (8B Instruct 2512)·Ministral 3 (8B Reasoning 2512)·Mistral Large 3 (675B Instruct 2512)·Mistral Large 3·Devstral Small 1.1·Devstral Medium·Mistral Small 3.2 24B Instruct·Mistral Small 3.1 24B Base·Mistral Small 3.1 24B Instruct·Mistral Small 3 24B Instruct·Pixtral Large·Ministral 8B Instruct·Mistral Small·Pixtral-12B·Mistral Large 2·Mistral NeMo Instruct

    Moonshot AI

    8 models
    Kimi K2.7 Code·Kimi K2.7 Code HighSpeed·Kimi K2.6·Kimi K2.5·Kimi K2 0905·Kimi K2-Instruct-0905·Kimi K2-Thinking-0905·Kimi K2 Instruct

    Nous Research

    1 models
    Hermes 3 70B

    NVIDIA

    4 models
    Nemotron 3 Ultra (550B A55B)·Nemotron 3 Super (120B A12B)·Nemotron 3 Nano (30B A3B)·Nemotron Nano 9B v2

    StepFun

    1 models
    Step-3.5-Flash

    Unisound

    1 models
    U2

    Xiaomi

    3 models
    MiMo-V2.5-Pro·MiMo-V2.5·MiMo-V2-Flash

    Z AI

    19 models
    GLM-5.2·GLM-5.1·GLM-5·GLM-4.7-Flash·GLM-4.7·GLM-4.6·GLM-4.5V·GLM-4.5·GLM-4.5-Air·GLM-4-32B-0414-128K·GLM-4.5-AirX·GLM-4.5-Flash·GLM-4.5-X·GLM-4.6V·GLM-4.6V-Flash·GLM-4.6V-FlashX·GLM-4.7-FlashX·GLM-5-Turbo·GLM-5V-Turbo
    Best AI for Reasoning 2026 — LLM Reasoning Leaderboard | AnotherWrapper