Comparison of AI Models across Intelligence, Performance, Price | Artificial Analysis

Comparison of Models: Intelligence, Performance & Price Analysis

Name: Artificial Analysis Intelligence Index
Creator: Artificial Analysis
License: https://creativecommons.org/licenses/by/4.0/

Comparison and analysis of AI models across key performance metrics including quality, price, output speed, latency, context window & others. Click on any model to see detailed metrics. For more details including relating to our methodology, see our FAQs.

Model Comparison Summary

Intelligence: Gemini 3 Pro Preview (high) logo

Gemini 3 Pro Preview (high) and GPT-5.2 (xhigh) logo

GPT-5.2 (xhigh) are the highest intelligence models, followed by Claude Opus 4.5 logo

Claude Opus 4.5 & GPT-5.1 (high) logo

GPT-5.1 (high).Output Speed (tokens/s): Gemini 2.5 Flash-Lite (Sep) logo

Gemini 2.5 Flash-Lite (Sep) (670 t/s) and Gemini 2.5 Flash-Lite (Sep) logo

Gemini 2.5 Flash-Lite (Sep) (487 t/s) are the fastest models, followed by Nova Micro logo

Nova Micro & Granite 3.3 8B logo

Granite 3.3 8B.Latency (seconds): Apriel-v1.5-15B-Thinker logo

Apriel-v1.5-15B-Thinker (0.16s) and DeepSeek-OCR logo

DeepSeek-OCR (0.19s) are the lowest latency models, followed by

NVIDIA Nemotron Nano 12B v2 VL & QwQ 32B-Preview logo

QwQ 32B-Preview.Price ($ per M tokens): Gemma 3n E4B logo

Gemma 3n E4B ($0.03) and DeepSeek-OCR logo

DeepSeek-OCR ($0.05) are the cheapest models, followed by Llama 3.2 1B logo

Llama 3.2 1B & Llama 3.2 3B logo

Llama 3.2 3B.Context Window: Llama 4 Scout logo

Llama 4 Scout (10m) and Grok 4 Fast logo

Grok 4 Fast (2m) are the largest context window models, followed by Grok 4 Fast logo

Grok 4 Fast & Grok 4.1 Fast logo

Grok 4.1 Fast.

Highlights

Further details

Model Name	Creator	License	Context Window	Further analysis
OpenAI
gpt-oss-120B (high)	OpenAI	Open	131k

Models compared: OpenAI: GPT 4o Audio, GPT 4o Realtime, GPT 4o Speech Pipeline, GPT Realtime, GPT Realtime Mini (Oct '25), GPT-3.5 Turbo, GPT-3.5 Turbo (0125), GPT-3.5 Turbo (0301), GPT-3.5 Turbo (0613), GPT-3.5 Turbo (1106), GPT-3.5 Turbo Instruct, GPT-4, GPT-4 Turbo, GPT-4 Turbo (0125), GPT-4 Turbo (1106), GPT-4 Vision, GPT-4.1, GPT-4.1 mini, GPT-4.1 nano, GPT-4.5 (Preview), GPT-4o (Apr), GPT-4o (Aug), GPT-4o (ChatGPT), GPT-4o (Mar), GPT-4o (May), GPT-4o (Nov), GPT-4o Realtime (Dec), GPT-4o mini, GPT-4o mini Realtime (Dec), GPT-5 (ChatGPT), GPT-5 (high), GPT-5 (low), GPT-5 (medium), GPT-5 (minimal), GPT-5 Codex (high), GPT-5 Pro (high), GPT-5 mini (high), GPT-5 mini (medium), GPT-5 mini (minimal), GPT-5 nano (high), GPT-5 nano (medium), GPT-5 nano (minimal), GPT-5.1, GPT-5.1 (high), GPT-5.1 Codex (high), GPT-5.1 Codex mini (high), GPT-5.2, GPT-5.2 (xhigh), gpt-oss-120B (high), gpt-oss-120B (low), gpt-oss-20B (high), gpt-oss-20B (low), o1, o1-mini, o1-preview, o1-pro, o3, o3-mini, o3-mini (high), o3-pro, and o4-mini (high), Meta: Code Llama 70B, Llama 2 Chat 13B, Llama 2 Chat 70B, Llama 2 Chat 7B, Llama 3 70B, Llama 3 8B, Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, Llama 3.2 11B (Vision), Llama 3.2 1B, Llama 3.2 3B, Llama 3.2 90B (Vision), Llama 3.3 70B, Llama 4 Behemoth, Llama 4 Maverick, Llama 4 Scout, and Llama 65B, Google: Gemini 1.0 Pro, Gemini 1.0 Ultra, Gemini 1.5 Flash (May), Gemini 1.5 Flash (Sep), Gemini 1.5 Flash-8B, Gemini 1.5 Pro (May), Gemini 1.5 Pro (Sep), Gemini 2.0 Flash, Gemini 2.0 Flash (exp), Gemini 2.0 Flash Thinking exp. (Dec), Gemini 2.0 Flash Thinking exp. (Jan), Gemini 2.0 Flash-Lite (Feb), Gemini 2.0 Flash-Lite (Preview), Gemini 2.0 Pro Experimental, Gemini 2.5 Flash, Gemini 2.5 Flash Live Preview, Gemini 2.5 Flash Native Audio, Gemini 2.5 Flash Native Audio Dialog, Gemini 2.5 Flash (Sep), Gemini 2.5 Flash-Lite, Gemini 2.5 Flash-Lite (Sep), Gemini 2.5 Pro, Gemini 2.5 Pro (Mar), Gemini 2.5 Pro (May), Gemini 3 Pro Preview (high), Gemini 3 Pro Preview (low), Gemini Experimental (Nov), Gemma 2 27B, Gemma 2 2B, Gemma 2 9B, Gemma 3 12B, Gemma 3 1B, Gemma 3 270M, Gemma 3 27B, Gemma 3 4B, Gemma 3n E2B, Gemma 3n E4B, Gemma 3n E4B (May), Gemma 7B, PALM-2, Whisperwind, fiercefalcon (Non-reasoning), and fiercefalcon (Reasoning), Anthropic: Claude 2.0, Claude 2.1, Claude 3 Haiku, Claude 3 Opus, Claude 3 Sonnet, Claude 3.5 Haiku, Claude 3.5 Sonnet (June), Claude 3.5 Sonnet (Oct), Claude 3.7 Sonnet, Claude 4 Opus, Claude 4 Sonnet, Claude 4.1 Opus, Claude 4.5 Haiku, Claude 4.5 Sonnet, Claude Instant, and Claude Opus 4.5, Mistral: Codestral (Jan), Codestral (May), Codestral-Mamba, Devstral 2, Devstral Medium, Devstral Small, Devstral Small (May), Devstral Small 2, Magistral Medium 1, Magistral Medium 1.1, Magistral Medium 1.2, Magistral Small 1, Magistral Small 1.1, Magistral Small 1.2, Ministral 14B (Dec '25), Ministral 3B, Ministral 3B (Dec '25), Ministral 8B, Ministral 8B (Dec '25), Mistral 7B, Mistral Large (Feb), Mistral Large 2 (Jul), Mistral Large 2 (Nov), Mistral Large 3, Mistral Medium, Mistral Medium 3, Mistral Medium 3.1, Mistral NeMo, Mistral Saba, Mistral Small (Feb), Mistral Small (Sep), Mistral Small 3, Mistral Small 3.1, Mistral Small 3.2, Mixtral 8x22B, Mixtral 8x7B, Pixtral 12B, and Pixtral Large, DeepSeek: DeepSeek Coder V2 Lite, DeepSeek LLM 67B (V1), DeepSeek Prover V2 671B, DeepSeek R1 (FP4), DeepSeek R1 (Jan), DeepSeek R1 0528, DeepSeek R1 0528 Qwen3 8B, DeepSeek R1 Distill Llama 70B, DeepSeek R1 Distill Llama 8B, DeepSeek R1 Distill Qwen 1.5B, DeepSeek R1 Distill Qwen 14B, DeepSeek R1 Distill Qwen 32B, DeepSeek V3 (Dec), DeepSeek V3 0324, DeepSeek V3.1, DeepSeek V3.1 Terminus, DeepSeek V3.2, DeepSeek V3.2 Exp, DeepSeek V3.2 Speciale, DeepSeek-Coder-V2, DeepSeek-OCR, DeepSeek-V2, DeepSeek-V2.5, DeepSeek-V2.5 (Dec), DeepSeek-VL2, and Janus Pro 7B, Perplexity: PPLX-70B Online, PPLX-7B-Online, R1 1776, Sonar, Sonar 3.1 Huge, Sonar 3.1 Large, Sonar 3.1 Small , Sonar Large, Sonar Pro, Sonar Reasoning, Sonar Reasoning Pro, and Sonar Small, xAI: Grok 2, Grok 3, Grok 3 Reasoning Beta, Grok 3 mini, Grok 3 mini Reasoning (low), Grok 3 mini Reasoning (high), Grok 4, Grok 4 Fast, Grok 4 Fast 1111 (Reasoning), Grok 4 mini (0908), Grok 4.1 Fast, Grok 4.1 Fast v4, Grok Beta, Grok Code Fast 1, Grok Voice, Grok-1, and test model, OpenChat: OpenChat 3.5, Amazon: Nova 2.0 Lite, Nova 2.0 Lite (high), Nova 2.0 Lite (low), Nova 2.0 Lite (medium), Nova 2.0 Omni, Nova 2.0 Omni (high), Nova 2.0 Omni (low), Nova 2.0 Omni (medium), Nova 2.0 Pro Preview, Nova 2.0 Pro Preview (high), Nova 2.0 Pro Preview (low), Nova 2.0 Pro Preview (medium), Nova 2.0 Realtime, Nova 2.0 Sonic, Nova Lite, Nova Micro, Nova Premier, and Nova Pro, Microsoft Azure: Phi-3 Medium 14B, Phi-3 Mini, Phi-4, Phi-4 Mini, Phi-4 Multimodal, Phi-4 mini reasoning, Phi-4 reasoning, Phi-4 reasoning plus, Yosemite-1-1, Yosemite-1-1-d36, Yosemite 1.1 d36 Updated, Yosemite-1-1-d64, Yosemite 1.1 d64 Updated, and Yosemite, Liquid AI: LFM 1.3B, LFM 3B, LFM 40B, LFM2 1.2B, LFM2 2.6B, and LFM2 8B A1B, Upstage: Solar Mini, Solar Pro, Solar Pro (Nov), Solar Pro 2, and Solar Pro 2 , Databricks: DBRX, MiniMax: MiniMax M1 40k, MiniMax M1 80k, MiniMax-M2, and MiniMax-Text-01, NVIDIA: Cosmos Nemotron 34B, Llama 3.1 Nemotron 70B, Llama 3.1 Nemotron Nano 4B v1.1, Llama 3.1 Nemotron Nano 8B, Llama 3.3 Nemotron Nano 8B, Llama Nemotron Ultra, Llama 3.3 Nemotron Super 49B, Llama Nemotron Super 49B v1.5, Nemotron 3 Nano (30B A3B), NVIDIA Nemotron 3 Nano, NVIDIA Nemotron Nano 12B v2 VL, and NVIDIA Nemotron Nano 9B V2, StepFun: Step-2, Step-2-Mini, Step3, step-1-128k, step-1-256k, step-1-32k, step-1-8k, step-1-flash, step-2-16k-exp, and step-r1-v-mini, IBM: Granite 3.0 2B, Granite 3.0 8B, Granite 3.3 8B, Granite 4.0 1B, Granite 4.0 350M, Granite 4.0 8B, Granite 4.0 H 1B, Granite 4.0 H 350M, Granite 4.0 H Small, Granite 4.0 Micro, Granite 4.0 Tiny, and Granite Vision 3.3 2B, Inceptionlabs: Mercury, Mercury Coder Mini, Mercury Coder Small, and Mercury Instruct, Reka AI: Reka Core, Reka Edge, Reka Flash (Feb), Reka Flash, Reka Flash 3, and Reka Flash 3.1, LG AI Research: EXAONE 4.0 32B, EXAONE Deep 32B, and Exaone 4.0 1.2B, Xiaomi: MiMo 7B RL and Mimo-v2-flash-1207-sft, Baidu: ERNIE 4.5, ERNIE 4.5 0.3B, ERNIE 4.5 21B A3B, ERNIE 4.5 300B A47B, ERNIE 4.5 VL 28B A3B, ERNIE 4.5 VL 424B A47B, ERNIE 5.0 Thinking Preview, and ERNIE X1, Baichuan: Baichuan 4 and Baichuan M1 (Preview), vercel: v0-1.0-md, Apple: Apple On-Device and FastVLM, Other: LLaVA-v1.5-7B, Tencent: Hunyuan A13B, Hunyuan 80B A13B, Hunyuan T1, and Hunyuan-TurboS, Prime Intellect: INTELLECT-3, Motif Technologies: Motif-2-12.7B, Korea Telecom: midm-250-pro-rsnsft, Z AI: GLM-4 32B, GLM-4 9B, GLM-4-Air, GLM-4 AirX, GLM-4 FlashX, GLM-4-Long, GLM-4-Plus, GLM-4.1V 9B Thinking, GLM-4.5, GLM-4.5-Air, GLM-4.5V, GLM-4.6, GLM-4.6V, GLM-Z1 32B, GLM-Z1 9B, GLM-Z1 Rumination 32B, and GLM-Zero (Preview), Cohere: Aya Expanse 32B, Aya Expanse 8B, Command, Command A, Command Light, Command R7B, Command-R, Command-R (Mar), Command-R+ (Apr), and Command-R+, Bytedance: Duobao 1.5 Pro, Seed-Thinking-v1.5, Skylark Lite, and Skylark Pro, AI21 Labs: Jamba 1.5 Large, Jamba 1.5 Large (Feb), Jamba 1.5 Mini, Jamba 1.5 Mini (Feb), Jamba 1.6 Large, Jamba 1.6 Mini, Jamba 1.7 Large, Jamba 1.7 Mini, Jamba Instruct, and Jamba Reasoning 3B, Snowflake: Arctic and Snowflake Llama 3.3 70B, PaddlePaddle: PaddleOCR-VL-0.9B, Alibaba: QwQ-32B, QwQ 32B-Preview, Qwen Chat 14B, Qwen Chat 72B, Qwen Chat 7B, Qwen1.5 Chat 110B, Qwen1.5 Chat 14B, Qwen1.5 Chat 32B, Qwen1.5 Chat 72B, Qwen1.5 Chat 7B, Qwen2 72B, Qwen2 Instruct 7B, Qwen2 Instruct A14B 57B, Qwen2-VL 72B, Qwen2.5 Coder 32B, Qwen2.5 Coder 7B , Qwen2.5 Instruct 14B, Qwen2.5 Instruct 32B, Qwen2.5 72B, Qwen2.5 Instruct 7B, Qwen2.5 Max, Qwen2.5 Max 01-29, Qwen2.5 Omni 7B, Qwen2.5 Plus, Qwen2.5 Turbo, Qwen2.5 VL 72B, Qwen2.5 VL 7B, Qwen3 0.6B, Qwen3 1.7B, Qwen3 14B, Qwen3 235B, Qwen3 235B A22B 2507, Qwen3 235B 2507, Qwen3 30B, Qwen3 30B A3B 2507, Qwen3 32B, Qwen3 4B, Qwen3 4B 2507, Qwen3 8B, Qwen3 Coder 30B A3B, Qwen3 Coder 480B, Qwen3 Max, Qwen3 Max (Preview), Qwen3 Max Thinking, Qwen3 Next 80B A3B, Qwen3 Omni 30B A3B, Qwen3 VL 235B A22B, Qwen3 VL 30B A3B, Qwen3 VL 32B, Qwen3 VL 4B, and Qwen3 VL 8B, InclusionAI: Ling-1T, Ling-flash-2.0, Ling-mini-2.0, Ring-1T, and Ring-flash-2.0, 01.AI: Yi-Large and Yi-Lightning, and ByteDance Seed: Doubao Seed Code and Seed-OSS-36B-Instruct.

Artificial Analysis Intelligence Index by Open Weights vs Proprietary

Artificial Analysis Intelligence Index v3.0 incorporates 10 evaluations: MMLU-Pro, GPQA Diamond, Humanity's Last Exam, LiveCodeBench, SciCode, AIME 2025, IFBench, AA-LCR, Terminal-Bench Hard, 𝜏²-Bench Telecom

+ Add model from specific provider

Proprietary

Open Weights

Combination metric covering multiple dimensions of intelligence - the simplest way to compare how smart models are. Version 3.0 was released in September 2025 and includes: MMLU-Pro, GPQA Diamond, Humanity's Last Exam, LiveCodeBench, SciCode, AIME 2025, IFBench, AA-LCR, Terminal-Bench Hard, 𝜏²-Bench Telecom. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).

Artificial Analysis Intelligence Index by Model Type

+ Add model from specific provider

Reasoning Model

Non-Reasoning Model

Artificial Analysis Omniscience

Back to Navigation

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

+ Add model from specific provider

{"@context":"https://schema.org","@type":"Dataset","name":"AA-Omniscience Index","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://creativecommons.org/licenses/by/4.0/","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":"modelName,omniscienceIndex,detailsUrl,isLabClaimedValue\nGemini 3 Pro Preview (high),12.867,/models/gemini-3-pro/providers,false\nClaude Opus 4.5,10.233,/models/claude-opus-4-5-thinking/providers,false\nClaude 4.1 Opus,4.933,/models/claude-4-1-opus-thinking/providers,false\nGPT-5.1 (high),2.2,/models/gpt-5-1/providers,false\nGrok 4,0.95,/models/grok-4/providers,false\nGemini 3 Pro Preview (low),-1.05,/models/gemini-3-pro-low/providers,false\nClaude 4.5 Sonnet,-2.083,/models/claude-4-5-sonnet-thinking/providers,false\nGPT-5.2 (xhigh),-4.317,/models/gpt-5-2/providers,false\nClaude 4.5 Haiku,-5.667,/models/claude-4-5-haiku-reasoning/providers,false\nClaude Opus 4.5,-6.45,/models/claude-opus-4-5/providers,false\nGrok 3 mini Reasoning (high),-6.9,/models/grok-3-mini-reasoning/providers,false\nClaude 4.5 Haiku,-7.95,/models/claude-4-5-haiku/providers,false\nClaude 4.5 Sonnet,-10.65,/models/claude-4-5-sonnet/providers,false\nGPT-5 (high),-11.1,/models/gpt-5/providers,false\nGPT-5 mini (medium),-12.933,/models/gpt-5-mini-medium/providers,false\nGPT-5 (low),-12.933,/models/gpt-5-low/providers,false\nGPT-5 (medium),-13.733,/models/gpt-5-medium/providers,false\no3,-17.183,/models/o3/providers,false\nGemini 2.5 Pro,-17.95,/models/gemini-2-5-pro/providers,false\nLlama 3.1 405B,-18.167,/models/llama-3-1-instruct-405b/providers,false\nGPT-5.1 Codex mini (high),-18.283,/models/gpt-5-1-codex-mini/providers,false\nDeepSeek V3.2 Speciale,-19.233,/models/deepseek-v3-2-speciale/providers,false\nGPT-5 mini (high),-19.617,/models/gpt-5-mini/providers,false\nDeepSeek V3.2,-23.317,/models/deepseek-v3-2-reasoning/providers,false\nKimi K2 Thinking,-23.417,/models/kimi-k2-thinking/providers,false\nDeepSeek V3.1 Terminus,-26.7,/models/deepseek-v3-1-terminus-reasoning/providers,false\nGPT-5 nano (medium),-27.35,/models/gpt-5-nano-medium/providers,false\nMagistral Medium 1.2,-27.633,/models/magistral-medium-2509/providers,false\nKimi K2 0905,-28.35,/models/kimi-k2-0905/providers,false\nGPT-5 nano (high),-29.65,/models/gpt-5-nano/providers,false\nDeepSeek R1 0528,-29.667,/models/deepseek-r1/providers,false\nGrok 4 Fast,-30.5,/models/grok-4-fast-reasoning/providers,false\nGrok 4.1 Fast,-31.383,/models/grok-4-1-fast-reasoning/providers,false\nDeepSeek V3.2 Exp,-31.9,/models/deepseek-v3-2-reasoning-0925/providers,false\nDevstral Medium,-32.8,/models/devstral-medium/providers,false\nGLM-4.6,-33.25,/models/glm-4-6/providers,false\nHermes 4 405B,-35.067,/models/hermes-4-llama-3-1-405b/providers,false\nKAT-Coder-Pro V1,-35.533,/models/kat-coder-pro-v1/providers,false\nDoubao Seed Code,-35.933,/models/doubao-seed-code/providers,false\nGPT-5.1,-36.583,/models/gpt-5-1-non-reasoning/providers,false\nGPT-5 (minimal),-36.667,/models/gpt-5-minimal/providers,false\nERNIE 4.5 300B A47B,-36.833,/models/ernie-4-5-300b-a47b/providers,false\nHermes 4 405B,-37.367,/models/hermes-4-llama-3-1-405b-reasoning/providers,false\nGemini 2.5 Flash (Sep),-37.5,/models/gemini-2-5-flash-preview-09-2025-reasoning/providers,false\nGrok Code Fast 1,-38.033,/models/grok-code-fast-1/providers,false\nNova Premier,-38.317,/models/nova-premier/providers,false\nQwen3 Max Thinking,-39.783,/models/qwen3-max-thinking/providers,false\nMistral Large 3,-40.983,/models/mistral-large-3/providers,false\nGemini 2.5 Flash (Sep),-41.317,/models/gemini-2-5-flash-preview-09-2025/providers,false\nGPT-4.1,-42.133,/models/gpt-4-1/providers,false\nERNIE 5.0 Thinking Preview,-42.367,/models/ernie-5-0-thinking-preview/providers,false\nNVIDIA Nemotron Nano 9B V2,-43.217,/models/nvidia-nemotron-nano-9b-v2-reasoning/providers,false\nLlama 4 Maverick,-43.467,/models/llama-4-maverick/providers,false\nGemini 2.5 Flash-Lite (Sep),-43.717,/models/gemini-2-5-flash-lite-preview-09-2025/providers,false\nGLM-4.6,-43.883,/models/glm-4-6-reasoning/providers,false\nDeepSeek V3.1 Terminus,-44.583,/models/deepseek-v3-1-terminus/providers,false\nQwen3 Max,-44.9,/models/qwen3-max/providers,false\nQwen3 235B 2507,-45.383,/models/qwen3-235b-a22b-instruct-2507/providers,false\nLlama Nemotron Ultra,-46.2,/models/llama-3-1-nemotron-ultra-253b-v1-reasoning/providers,false\nGLM-4.5V,-46.417,/models/glm-4-5v-reasoning/providers,false\nQwen3 VL 235B A22B,-46.567,/models/qwen3-vl-235b-a22b-reasoning/providers,false\nDeepSeek R1 Distill Llama 70B,-47.433,/models/deepseek-r1-distill-llama-70b/providers,false\nLlama Nemotron Super 49B v1.5,-47.467,/models/llama-nemotron-super-49b-v1-5-reasoning/providers,false\nNova 2.0 Pro Preview (low),-47.5,/models/nova-2-0-pro-reasoning-low/providers,false\nQwen3 235B A22B 2507,-47.7,/models/qwen3-235b-a22b-instruct-2507-reasoning/providers,false\nMistral Medium 3.1,-47.9,/models/mistral-medium-3-1/providers,false\nDevstral 2,-47.917,/models/devstral-2/providers,false\nDeepSeek V3.2,-48.683,/models/deepseek-v3-2/providers,false\nMiniMax-M2,-49.533,/models/minimax-m2/providers,false\nNova 2.0 Pro Preview (medium),-50.3,/models/nova-2-0-pro-reasoning-medium/providers,false\nNova 2.0 Pro Preview,-50.367,/models/nova-2-0-pro/providers,false\nCommand A,-50.4,/models/command-a/providers,false\nHermes 4 70B,-50.717,/models/hermes-4-llama-3-1-70b-reasoning/providers,false\nMistral Small 3.2,-51.3,/models/mistral-small-3-2/providers,false\nNova 2.0 Omni (low),-51.4,/models/nova-2-0-omni-reasoning-low/providers,false\ngpt-oss-120B (high),-51.933,/models/gpt-oss-120b/providers,false\nDevstral Small,-51.967,/models/devstral-small/providers,false\nGrok 4.1 Fast,-52.317,/models/grok-4-1-fast/providers,false\nQwen3 Next 80B A3B,-52.783,/models/qwen3-next-80b-a3b-reasoning/providers,false\nLlama 4 Scout,-53.05,/models/llama-4-scout/providers,false\nQwen3 VL 32B,-53.233,/models/qwen3-vl-32b-reasoning/providers,false\nSeed-OSS-36B-Instruct,-53.533,/models/seed-oss-36b-instruct/providers,false\nQwen3 VL 8B,-53.8,/models/qwen3-vl-8b-instruct/providers,false\nQwen3 VL 235B A22B,-53.867,/models/qwen3-vl-235b-a22b-instruct/providers,false\nQwen3 VL 8B,-54.317,/models/qwen3-vl-8b-reasoning/providers,false\nGemini 2.5 Flash-Lite (Sep),-54.633,/models/gemini-2-5-flash-lite-preview-09-2025-reasoning/providers,false\nNova 2.0 Lite (low),-54.95,/models/nova-2-0-lite-reasoning-low/providers,false\nApriel-v1.5-15B-Thinker,-55.85,/models/apriel-v1-5-15b-thinker/providers,false\ngpt-oss-120B (low),-55.933,/models/gpt-oss-120b-low/providers,false\nQwen3 30B A3B 2507,-57.433,/models/qwen3-30b-a3b-2507-reasoning/providers,false\nSolar Pro 2,-57.533,/models/solar-pro-2-reasoning/providers,false\nNova 2.0 Lite (medium),-57.633,/models/nova-2-0-lite-reasoning-medium/providers,false\nDevstral Small 2,-58.883,/models/devstral-small-2/providers,false\nQwen3 VL 30B A3B,-59.133,/models/qwen3-vl-30b-a3b-reasoning/providers,false\nNova 2.0 Omni (medium),-59.7,/models/nova-2-0-omni-reasoning-medium/providers,false\nApriel-v1.6-15B-Thinker,-59.833,/models/apriel-v1-6-15b-thinker/providers,false\nNova 2.0 Lite,-60.483,/models/nova-2-0-lite/providers,false\nQwen3 Next 80B A3B,-60.483,/models/qwen3-next-80b-a3b-instruct/providers,false\ngpt-oss-20B (low),-60.6,/models/gpt-oss-20b-low/providers,false\nEXAONE 4.0 32B,-61.417,/models/exaone-4-0-32b-reasoning/providers,false\nGranite 4.0 H Small,-62.067,/models/granite-4-0-h-small/providers,false\nMotif-2-12.7B,-62.233,/models/motif-2-12-7b/providers,false\nQwen3 Omni 30B A3B,-62.417,/models/qwen3-omni-30b-a3b-reasoning/providers,false\nGLM-4.5-Air,-63.15,/models/glm-4-5-air/providers,false\nQwen3 VL 32B,-63.9,/models/qwen3-vl-32b-instruct/providers,false\nMinistral 3B (Dec '25),-63.967,/models/ministral-3b/providers,false\nQwen3 VL 30B A3B,-64.033,/models/qwen3-vl-30b-a3b-instruct/providers,false\nDeepSeek R1 0528 Qwen3 8B,-64.617,/models/deepseek-r1-qwen3-8b/providers,false\ngpt-oss-20B (high),-64.9,/models/gpt-oss-20b/providers,false\nQwen3 8B,-66.117,/models/qwen3-8b-instruct-reasoning/providers,false\nEXAONE 4.0 32B,-66.133,/models/exaone-4-0-32b/providers,false\nNVIDIA Nemotron Nano 12B v2 VL,-66.35,/models/nvidia-nemotron-nano-12b-v2-vl-reasoning/providers,false\nGPT-5 nano (minimal),-66.367,/models/gpt-5-nano-minimal/providers,false\nMagistral Small 1.2,-66.383,/models/magistral-small-2509/providers,false\nQwen3 30B A3B 2507,-66.8,/models/qwen3-30b-a3b-2507/providers,false\nMinistral 14B (Dec '25),-67.383,/models/ministral-14b/providers,false\nLing-flash-2.0,-67.45,/models/ling-flash-2-0/providers,false\nMinistral 8B (Dec '25),-69.983,/models/ministral-8b/providers,false\nOLMo 3 7B Think,-73.967,/models/olmo-3-7b-think/providers,false\nQwen3 8B,-75.4,/models/qwen3-8b-instruct/providers,false"}

AA-Omniscience Accuracy

AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer

+ Add model from specific provider

AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer

{"@context":"https://schema.org","@type":"Dataset","name":"AA-Omniscience Accuracy","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://creativecommons.org/licenses/by/4.0/","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":"modelName,omniscienceAccuracy,detailsUrl,isLabClaimedValue\nGemini 3 Pro Preview (high),0.5365,/models/gemini-3-pro/providers,false\nGemini 3 Pro Preview (low),0.46016666666666667,/models/gemini-3-pro-low/providers,false\nClaude Opus 4.5,0.43116666666666664,/models/claude-opus-4-5-thinking/providers,false\nGPT-5.2 (xhigh),0.4135,/models/gpt-5-2/providers,false\nGrok 4,0.39566666666666667,/models/grok-4/providers,false\nClaude Opus 4.5,0.389,/models/claude-opus-4-5/providers,false\nGPT-5 (high),0.38616666666666666,/models/gpt-5/providers,false\nGemini 2.5 Pro,0.37483333333333335,/models/gemini-2-5-pro/providers,false\nGPT-5 (medium),0.37383333333333335,/models/gpt-5-medium/providers,false\no3,0.3725,/models/o3/providers,false\nDeepSeek V3.2 Speciale,0.3675,/models/deepseek-v3-2-speciale/providers,false\nGPT-5 (low),0.3635,/models/gpt-5-low/providers,false\nClaude 4.1 Opus,0.35933333333333334,/models/claude-4-1-opus-thinking/providers,false\nGPT-5.1 (high),0.353,/models/gpt-5-1/providers,false\nDeepSeek V3.2,0.32216666666666666,/models/deepseek-v3-2-reasoning/providers,false\nClaude 4.5 Sonnet,0.309,/models/claude-4-5-sonnet-thinking/providers,false\nDeepSeek R1 0528,0.29283333333333333,/models/deepseek-r1/providers,false\nKimi K2 Thinking,0.29233333333333333,/models/kimi-k2-thinking/providers,false\nHermes 4 405B,0.2911666666666667,/models/hermes-4-llama-3-1-405b-reasoning/providers,false\nGPT-5.1,0.278,/models/gpt-5-1-non-reasoning/providers,false\nGPT-5 (minimal),0.27216666666666667,/models/gpt-5-minimal/providers,false\nDeepSeek V3.1 Terminus,0.27166666666666667,/models/deepseek-v3-1-terminus-reasoning/providers,false\nGemini 2.5 Flash (Sep),0.2698333333333333,/models/gemini-2-5-flash-preview-09-2025-reasoning/providers,false\nDeepSeek V3.2 Exp,0.26966666666666667,/models/deepseek-v3-2-reasoning-0925/providers,false\nClaude 4.5 Sonnet,0.2693333333333333,/models/claude-4-5-sonnet/providers,false\nQwen3 Max Thinking,0.26616666666666666,/models/qwen3-max-thinking/providers,false\nGPT-4.1,0.2608333333333333,/models/gpt-4-1/providers,false\nGemini 2.5 Flash (Sep),0.25766666666666665,/models/gemini-2-5-flash-preview-09-2025/providers,false\nGLM-4.6,0.25483333333333336,/models/glm-4-6-reasoning/providers,false\nHermes 4 405B,0.24933333333333332,/models/hermes-4-llama-3-1-405b/providers,false\nKimi K2 0905,0.24033333333333334,/models/kimi-k2-0905/providers,false\nDoubao Seed Code,0.23866666666666667,/models/doubao-seed-code/providers,false\nMistral Large 3,0.23683333333333334,/models/mistral-large-3/providers,false\nLlama 4 Maverick,0.23516666666666666,/models/llama-4-maverick/providers,false\nGrok 4.1 Fast,0.235,/models/grok-4-1-fast-reasoning/providers,false\nQwen3 Max,0.2335,/models/qwen3-max/providers,false\nERNIE 5.0 Thinking Preview,0.23183333333333334,/models/ernie-5-0-thinking-preview/providers,false\nGPT-5 mini (high),0.22966666666666666,/models/gpt-5-mini/providers,false\nDeepSeek V3.2,0.22766666666666666,/models/deepseek-v3-2/providers,false\nGrok Code Fast 1,0.2275,/models/grok-code-fast-1/providers,false\nDeepSeek V3.1 Terminus,0.22616666666666665,/models/deepseek-v3-1-terminus/providers,false\nHermes 4 70B,0.223,/models/hermes-4-llama-3-1-70b-reasoning/providers,false\nQwen3 235B A22B 2507,0.22116666666666668,/models/qwen3-235b-a22b-instruct-2507-reasoning/providers,false\nGrok 4 Fast,0.22033333333333333,/models/grok-4-fast-reasoning/providers,false\nLlama 3.1 405B,0.21833333333333332,/models/llama-3-1-instruct-405b/providers,false\nGPT-5.1 Codex mini (high),0.21733333333333332,/models/gpt-5-1-codex-mini/providers,false\nGPT-5 mini (medium),0.21233333333333335,/models/gpt-5-mini-medium/providers,false\nNova 2.0 Pro Preview (low),0.20983333333333334,/models/nova-2-0-pro-reasoning-low/providers,false\nNova 2.0 Pro Preview (medium),0.2095,/models/nova-2-0-pro-reasoning-medium/providers,false\nMiniMax-M2,0.20833333333333334,/models/minimax-m2/providers,false\nQwen3 VL 235B A22B,0.2045,/models/qwen3-vl-235b-a22b-reasoning/providers,false\nGLM-4.6,0.20266666666666666,/models/glm-4-6/providers,false\nGLM-4.5V,0.20133333333333334,/models/glm-4-5v-reasoning/providers,false\nMagistral Medium 1.2,0.20083333333333334,/models/magistral-medium-2509/providers,false\ngpt-oss-120B (high),0.20016666666666666,/models/gpt-oss-120b/providers,false\nDevstral 2,0.198,/models/devstral-2/providers,false\nQwen3 VL 235B A22B,0.19216666666666668,/models/qwen3-vl-235b-a22b-instruct/providers,false\nLlama Nemotron Ultra,0.192,/models/llama-3-1-nemotron-ultra-253b-v1-reasoning/providers,false\nQwen3 VL 8B,0.19166666666666668,/models/qwen3-vl-8b-instruct/providers,false\nNova Premier,0.18983333333333333,/models/nova-premier/providers,false\nQwen3 VL 8B,0.18983333333333333,/models/qwen3-vl-8b-reasoning/providers,false\nMistral Medium 3.1,0.1895,/models/mistral-medium-3-1/providers,false\nSolar Pro 2,0.18533333333333332,/models/solar-pro-2-reasoning/providers,false\nDeepSeek R1 Distill Llama 70B,0.185,/models/deepseek-r1-distill-llama-70b/providers,false\nKAT-Coder-Pro V1,0.18466666666666667,/models/kat-coder-pro-v1/providers,false\nGPT-5 nano (high),0.18283333333333332,/models/gpt-5-nano/providers,false\nQwen3 Next 80B A3B,0.18216666666666667,/models/qwen3-next-80b-a3b-reasoning/providers,false\nDevstral Medium,0.18166666666666667,/models/devstral-medium/providers,false\ngpt-oss-120B (low),0.1815,/models/gpt-oss-120b-low/providers,false\nERNIE 4.5 300B A47B,0.17833333333333334,/models/ernie-4-5-300b-a47b/providers,false\nNova 2.0 Omni (low),0.1775,/models/nova-2-0-omni-reasoning-low/providers,false\nQwen3 235B 2507,0.17583333333333334,/models/qwen3-235b-a22b-instruct-2507/providers,false\nNova 2.0 Lite (medium),0.17366666666666666,/models/nova-2-0-lite-reasoning-medium/providers,false\nSeed-OSS-36B-Instruct,0.17333333333333334,/models/seed-oss-36b-instruct/providers,false\nNova 2.0 Omni (medium),0.172,/models/nova-2-0-omni-reasoning-medium/providers,false\nGemini 2.5 Flash-Lite (Sep),0.17133333333333334,/models/gemini-2-5-flash-lite-preview-09-2025-reasoning/providers,false\nNova 2.0 Lite (low),0.1675,/models/nova-2-0-lite-reasoning-low/providers,false\nQwen3 Next 80B A3B,0.16716666666666666,/models/qwen3-next-80b-a3b-instruct/providers,false\nApriel-v1.6-15B-Thinker,0.166,/models/apriel-v1-6-15b-thinker/providers,false\nGPT-5 nano (medium),0.16383333333333333,/models/gpt-5-nano-medium/providers,false\nQwen3 VL 32B,0.16366666666666665,/models/qwen3-vl-32b-reasoning/providers,false\nClaude 4.5 Haiku,0.16183333333333333,/models/claude-4-5-haiku-reasoning/providers,false\nLlama Nemotron Super 49B v1.5,0.16083333333333333,/models/llama-nemotron-super-49b-v1-5-reasoning/providers,false\nQwen3 VL 30B A3B,0.15933333333333333,/models/qwen3-vl-30b-a3b-reasoning/providers,false\nNova 2.0 Pro Preview,0.15866666666666668,/models/nova-2-0-pro/providers,false\nGrok 4.1 Fast,0.158,/models/grok-4-1-fast/providers,false\nCommand A,0.15466666666666667,/models/command-a/providers,false\nQwen3 30B A3B 2507,0.15466666666666667,/models/qwen3-30b-a3b-2507-reasoning/providers,false\nApriel-v1.5-15B-Thinker,0.153,/models/apriel-v1-5-15b-thinker/providers,false\nGLM-4.5-Air,0.1505,/models/glm-4-5-air/providers,false\nDevstral Small 2,0.14983333333333335,/models/devstral-small-2/providers,false\nQwen3 VL 30B A3B,0.1475,/models/qwen3-vl-30b-a3b-instruct/providers,false\ngpt-oss-20B (high),0.1465,/models/gpt-oss-20b/providers,false\nQwen3 Omni 30B A3B,0.14383333333333334,/models/qwen3-omni-30b-a3b-reasoning/providers,false\nLlama 4 Scout,0.1435,/models/llama-4-scout/providers,false\nQwen3 30B A3B 2507,0.143,/models/qwen3-30b-a3b-2507/providers,false\nMistral Small 3.2,0.14266666666666666,/models/mistral-small-3-2/providers,false\nMotif-2-12.7B,0.14116666666666666,/models/motif-2-12-7b/providers,false\nQwen3 VL 32B,0.1405,/models/qwen3-vl-32b-instruct/providers,false\nDevstral Small,0.1395,/models/devstral-small/providers,false\nGrok 3 mini Reasoning (high),0.13866666666666666,/models/grok-3-mini-reasoning/providers,false\nLing-flash-2.0,0.13733333333333334,/models/ling-flash-2-0/providers,false\ngpt-oss-20B (low),0.13683333333333333,/models/gpt-oss-20b-low/providers,false\nGranite 4.0 H Small,0.1345,/models/granite-4-0-h-small/providers,false\nClaude 4.5 Haiku,0.13416666666666666,/models/claude-4-5-haiku/providers,false\nGemini 2.5 Flash-Lite (Sep),0.1335,/models/gemini-2-5-flash-lite-preview-09-2025/providers,false\nNVIDIA Nemotron Nano 12B v2 VL,0.1335,/models/nvidia-nemotron-nano-12b-v2-vl-reasoning/providers,false\nEXAONE 4.0 32B,0.13333333333333333,/models/exaone-4-0-32b-reasoning/providers,false\nNova 2.0 Lite,0.13283333333333333,/models/nova-2-0-lite/providers,false\nMagistral Small 1.2,0.12766666666666668,/models/magistral-small-2509/providers,false\nQwen3 8B,0.12733333333333333,/models/qwen3-8b-instruct-reasoning/providers,false\nMinistral 14B (Dec '25),0.12133333333333333,/models/ministral-14b/providers,false\nMinistral 8B (Dec '25),0.11816666666666667,/models/ministral-8b/providers,false\nDeepSeek R1 0528 Qwen3 8B,0.11816666666666667,/models/deepseek-r1-qwen3-8b/providers,false\nGPT-5 nano (minimal),0.11366666666666667,/models/gpt-5-nano-minimal/providers,false\nNVIDIA Nemotron Nano 9B V2,0.10733333333333334,/models/nvidia-nemotron-nano-9b-v2-reasoning/providers,false\nQwen3 8B,0.10283333333333333,/models/qwen3-8b-instruct/providers,false\nOLMo 3 7B Think,0.10166666666666667,/models/olmo-3-7b-think/providers,false\nEXAONE 4.0 32B,0.09933333333333333,/models/exaone-4-0-32b/providers,false\nMinistral 3B (Dec '25),0.07783333333333334,/models/ministral-3b/providers,false"}

AA-Omniscience Hallucination Rate

AA-Omniscience Hallucination Rate (lower is better) measures how often the model answers incorrectly when it should have refused or admitted to not knowing the answer. It is defined as the proportion of incorrect answers out of all non-correct responses, i.e. incorrect / (incorrect + partial answers + not attempted).

+ Add model from specific provider

{"@context":"https://schema.org","@type":"Dataset","name":"AA-Omniscience Hallucination Rate","creator":{"@type":"Organization","name":"Artificial Analysis","url":"https://artificialanalysis.ai"},"description":"AA-Omniscience Hallucination Rate (lower is better) measures how often the model answers incorrectly when it should have refused or admitted to not knowing the answer. It is defined as the proportion of incorrect answers out of all non-correct responses, i.e. incorrect / (incorrect + partial answers + not attempted).","measurementTechnique":"Independent test run by Artificial Analysis on dedicated hardware.","spatialCoverage":"Worldwide","keywords":["analytics","llm","AI","benchmark","model","gpt","claude"],"license":"https://creativecommons.org/licenses/by/4.0/","isAccessibleForFree":true,"citation":"Artificial Analysis (2025). LLM benchmarks dataset. https://artificialanalysis.ai","data":"modelName,omniscienceHallucinationRate,detailsUrl,isLabClaimedValue\nQwen3 8B,0.955043655953929,/models/qwen3-8b-instruct/providers,false\nQwen3 30B A3B 2507,0.9463243873978997,/models/qwen3-30b-a3b-2507/providers,false\nLing-flash-2.0,0.9410741885625966,/models/ling-flash-2-0/providers,false\nHermes 4 70B,0.9397254397254398,/models/hermes-4-llama-3-1-70b-reasoning/providers,false\nHermes 4 405B,0.9379261697625205,/models/hermes-4-llama-3-1-405b-reasoning/providers,false\nOLMo 3 7B Think,0.9365491651205937,/models/olmo-3-7b-think/providers,false\nSolar Pro 2,0.9337152209492635,/models/solar-pro-2-reasoning/providers,false\ngpt-oss-20B (high),0.9320445225541887,/models/gpt-oss-20b/providers,false\nGLM-4.6,0.9308879445314248,/models/glm-4-6-reasoning/providers,false\nNova 2.0 Omni (medium),0.928743961352657,/models/nova-2-0-omni-reasoning-medium/providers,false\nMinistral 8B (Dec '25),0.9276129276129276,/models/ministral-8b/providers,false\nQwen3 Next 80B A3B,0.9269561737042226,/models/qwen3-next-80b-a3b-instruct/providers,false\nDeepSeek V3.2,0.9251186879585671,/models/deepseek-v3-2/providers,false\nQwen3 VL 30B A3B,0.9241446725317694,/models/qwen3-vl-30b-a3b-instruct/providers,false\nGPT-4.1,0.9228861330326945,/models/gpt-4-1/providers,false\nGLM-4.5-Air,0.9205414949970571,/models/glm-4-5-air/providers,false\nNVIDIA Nemotron Nano 12B v2 VL,0.9197922677437969,/models/nvidia-nemotron-nano-12b-v2-vl-reasoning/providers,false\nApriel-v1.6-15B-Thinker,0.916466826538769,/models/apriel-v1-6-15b-thinker/providers,false\nNova 2.0 Lite (medium),0.9076240419524002,/models/nova-2-0-lite-reasoning-medium/providers,false\nMagistral Small 1.2,0.9073366450133741,/models/magistral-small-2509/providers,false\nQwen3 VL 32B,0.9069226294357184,/models/qwen3-vl-32b-instruct/providers,false\ngpt-oss-120B (low),0.9051109753614335,/models/gpt-oss-120b-low/providers,false\nMinistral 14B (Dec '25),0.904969650986343,/models/ministral-14b/providers,false\nQwen3 Max Thinking,0.9048376107199637,/models/qwen3-max-thinking/providers,false\nQwen3 VL 8B,0.9047521086196256,/models/qwen3-vl-8b-reasoning/providers,false\nQwen3 VL 235B A22B,0.904683309263462,/models/qwen3-vl-235b-a22b-instruct/providers,false\nGemini 2.5 Flash (Sep),0.9036820835204311,/models/gemini-2-5-flash-preview-09-2025/providers,false\nQwen3 8B,0.9035523300229182,/models/qwen3-8b-instruct-reasoning/providers,false\nQwen3 VL 8B,0.902680412371134,/models/qwen3-vl-8b-instruct/providers,false\nNova 2.0 Pro Preview (medium),0.9013282732447818,/models/nova-2-0-pro-reasoning-medium/providers,false\ngpt-oss-120B (high),0.899562408835174,/models/gpt-oss-120b/providers,false\nQwen3 Omni 30B A3B,0.8970216079423788,/models/qwen3-omni-30b-a3b-reasoning/providers,false\nQwen3 235B A22B 2507,0.8964262786218703,/models/qwen3-235b-a22b-instruct-2507-reasoning/providers,false\nQwen3 VL 30B A3B,0.8929421094369548,/models/qwen3-vl-30b-a3b-reasoning/providers,false\nGPT-5.1,0.891735918744229,/models/gpt-5-1-non-reasoning/providers,false\nQwen3 Max,0.8904109589041096,/models/qwen3-max/providers,false\nMotif-2-12.7B,0.8889967009509024,/models/motif-2-12-7b/providers,false\nMiniMax-M2,0.8888421052631579,/models/minimax-m2/providers,false\nGemini 2.5 Pro,0.8866968808317782,/models/gemini-2-5-pro/providers,false\nDeepSeek V3.2 Speciale,0.8851119894598155,/models/deepseek-v3-2-speciale/providers,false\nGemini 2.5 Flash (Sep),0.883131705090162,/models/gemini-2-5-flash-preview-09-2025-reasoning/providers,false\nGemini 3 Pro Preview (high),0.8798993167925206,/models/gemini-3-pro/providers,false\nGPT-5 (minimal),0.8777192580719029,/models/gpt-5-minimal/providers,false\nGPT-5 nano (minimal),0.8770214366303122,/models/gpt-5-nano-minimal/providers,false\nLlama 4 Maverick,0.8757899324471562,/models/llama-4-maverick/providers,false\nGranite 4.0 H Small,0.8725207009435779,/models/granite-4-0-h-small/providers,false\nGemini 3 Pro Preview (low),0.8718740351960481,/models/gemini-3-pro-low/providers,false\nDevstral Small 2,0.8688492452460302,/models/devstral-small-2/providers,false\nDeepSeek V3.1 Terminus,0.8684040491061813,/models/deepseek-v3-1-terminus/providers,false\nQwen3 Next 80B A3B,0.8681475443244345,/models/qwen3-next-80b-a3b-reasoning/providers,false\no3,0.8674634794156707,/models/o3/providers,false\nDeepSeek R1 0528 Qwen3 8B,0.8667548667548668,/models/deepseek-r1-qwen3-8b/providers,false\nNova 2.0 Pro Preview (low),0.8666947901286648,/models/nova-2-0-pro-reasoning-low/providers,false\nGemini 2.5 Flash-Lite (Sep),0.8660498793242156,/models/gemini-2-5-flash-lite-preview-09-2025-reasoning/providers,false\nEXAONE 4.0 32B,0.8625,/models/exaone-4-0-32b-reasoning/providers,false\nQwen3 30B A3B 2507,0.8623817034700315,/models/qwen3-30b-a3b-2507-reasoning/providers,false\nNova 2.0 Lite (low),0.8612612612612612,/models/nova-2-0-lite-reasoning-low/providers,false\ngpt-oss-20B (low),0.8605908476539873,/models/gpt-oss-20b-low/providers,false\nSeed-OSS-36B-Instruct,0.8572580645161291,/models/seed-oss-36b-instruct/providers,false\nERNIE 5.0 Thinking Preview,0.8533304404426123,/models/ernie-5-0-thinking-preview/providers,false\nNova 2.0 Lite,0.8506630789928887,/models/nova-2-0-lite/providers,false\nMistral Large 3,0.8473465822231928,/models/mistral-large-3/providers,false\nEXAONE 4.0 32B,0.844559585492228,/models/exaone-4-0-32b/providers,false\nDevstral 2,0.8443474646716542,/models/devstral-2/providers,false\nQwen3 VL 235B A22B,0.8424470982610518,/models/qwen3-vl-235b-a22b-reasoning/providers,false\nNova 2.0 Omni (low),0.8407294832826747,/models/nova-2-0-omni-reasoning-low/providers,false\nApriel-v1.5-15B-Thinker,0.8400236127508854,/models/apriel-v1-5-15b-thinker/providers,false\nDeepSeek R1 0528,0.8336082960169692,/models/deepseek-r1/providers,false\nGLM-4.5V,0.8332637729549248,/models/glm-4-5v-reasoning/providers,false\nQwen3 VL 32B,0.8322040653646872,/models/qwen3-vl-32b-reasoning/providers,false\nMistral Medium 3.1,0.824799506477483,/models/mistral-medium-3-1/providers,false\nDeepSeek V3.2,0.8192771084337349,/models/deepseek-v3-2-reasoning/providers,false\nGPT-5 (medium),0.8163428267234496,/models/gpt-5-medium/providers,false\nGPT-5 (high),0.8099375509095845,/models/gpt-5/providers,false\nLlama Nemotron Ultra,0.8094059405940595,/models/llama-3-1-nemotron-ultra-253b-v1-reasoning/providers,false\nDeepSeek R1 Distill Llama 70B,0.808997955010225,/models/deepseek-r1-distill-llama-70b/providers,false\nGrok 4.1 Fast,0.8089865399841647,/models/grok-4-1-fast/providers,false\nDeepSeek V3.2 Exp,0.8060246462802373,/models/deepseek-v3-2-reasoning-0925/providers,false\nHermes 4 405B,0.7992895204262878,/models/hermes-4-llama-3-1-405b/providers,false\nNova 2.0 Pro Preview,0.7872424722662441,/models/nova-2-0-pro/providers,false\nLlama 4 Scout,0.7869235259778167,/models/llama-4-scout/providers,false\nGrok Code Fast 1,0.786839266450917,/models/grok-code-fast-1/providers,false\nDoubao Seed Code,0.7854640980735552,/models/doubao-seed-code/providers,false\nCommand A,0.7791798107255521,/models/command-a/providers,false\nGPT-5.2 (xhigh),0.7786302926967889,/models/gpt-5-2/providers,false\nMinistral 3B (Dec '25),0.7780589192120008,/models/ministral-3b/providers,false\nGPT-5 (low),0.7742864624247185,/models/gpt-5-low/providers,false\nDevstral Small,0.7660275033895022,/models/devstral-small/providers,false\nMistral Small 3.2,0.7647744945567652,/models/mistral-small-3-2/providers,false\nQwen3 235B 2507,0.7640040444893832,/models/qwen3-235b-a22b-instruct-2507/providers,false\nLlama Nemotron Super 49B v1.5,0.7572989076464747,/models/llama-nemotron-super-49b-v1-5-reasoning/providers,false\nKimi K2 Thinking,0.7439943476212906,/models/kimi-k2-thinking/providers,false\nClaude Opus 4.5,0.7422258592471358,/models/claude-opus-4-5/providers,false\nDeepSeek V3.1 Terminus,0.7395881006864988,/models/deepseek-v3-1-terminus-reasoning/providers,false\nGrok 4.1 Fast,0.7174291938997821,/models/grok-4-1-fast-reasoning/providers,false\nNova Premier,0.707261880271549,/models/nova-premier/providers,false\nKimi K2 0905,0.6895568231680561,/models/kimi-k2-0905/providers,false\nGrok 4 Fast,0.6737922188969645,/models/grok-4-fast-reasoning/providers,false\nGLM-4.6,0.6711956521739131,/models/glm-4-6/providers,false\nERNIE 4.5 300B A47B,0.665314401622718,/models/ernie-4-5-300b-a47b/providers,false\nKAT-Coder-Pro V1,0.6623058053965658,/models/kat-coder-pro-v1/providers,false\nGemini 2.5 Flash-Lite (Sep),0.6585881900365455,/models/gemini-2-5-flash-lite-preview-09-2025/providers,false\nGrok 4,0.638996138996139,/models/grok-4/providers,false\nDevstral Medium,0.6228105906313646,/models/devstral-medium/providers,false\nNVIDIA Nemotron Nano 9B V2,0.6043689320388349,/models/nvidia-nemotron-nano-9b-v2-reasoning/providers,false\nMagistral Medium 1.2,0.5970802919708029,/models/magistral-medium-2509/providers,false\nGPT-5 nano (high),0.5865796451152355,/models/gpt-5-nano/providers,false\nClaude Opus 4.5,0.5780837972458248,/models/claude-opus-4-5-thinking/providers,false\nGPT-5 mini (high),0.5527909995672868,/models/gpt-5-mini/providers,false\nGPT-5 nano (medium),0.523021726131154,/models/gpt-5-nano-medium/providers,false\nClaude 4.5 Sonnet,0.5143704379562044,/models/claude-4-5-sonnet/providers,false\nLlama 3.1 405B,0.511727078891258,/models/llama-3-1-instruct-405b/providers,false\nGPT-5.1 (high),0.5115919629057187,/models/gpt-5-1/providers,false\nGPT-5.1 Codex mini (high),0.5112862010221465,/models/gpt-5-1-codex-mini/providers,false\nClaude 4.1 Opus,0.4838709677419355,/models/claude-4-1-opus-thinking/providers,false\nClaude 4.5 Sonnet,0.47732754462132176,/models/claude-4-5-sonnet-thinking/providers,false\nGPT-5 mini (medium),0.43377063055438003,/models/gpt-5-mini-medium/providers,false\nClaude 4.5 Haiku,0.2606880095446411,/models/claude-4-5-haiku-reasoning/providers,false\nClaude 4.5 Haiku,0.2467757459095284,/models/claude-4-5-haiku/providers,false\nGrok 3 mini Reasoning (high),0.24109907120743035,/models/grok-3-mini-reasoning/providers,false"}

Intelligence vs. Price

Artificial Analysis Intelligence Index; Price: USD per 1M Tokens

+ Add model from specific provider

Most attractive quadrant

Alibaba

Allen Institute for AI

Amazon

Anthropic

DeepSeek

Google

Kimi

Meta

MiniMax

Mistral

NVIDIA

OpenAI

xAI

Z AI

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Intelligence vs. Output Speed

Artificial Analysis Intelligence Index; Output Speed: Output Tokens per Second

+ Add model from specific provider

Most attractive quadrant

Alibaba

Allen Institute for AI

Amazon

Anthropic

DeepSeek

Google

Kimi

KwaiKAT

Meta

MiniMax

Mistral

NVIDIA

OpenAI

ServiceNow

xAI

Z AI

There is a trade-off between model quality and output speed, with higher intelligence models typically having lower output speed.

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Intelligence vs. End-to-End Response Time

Artificial Analysis Intelligence Index; Seconds to Output 500 Tokens, including reasoning model 'thinking' time; Lower is better

+ Add model from specific provider

Most attractive quadrant

Alibaba

Allen Institute for AI

Amazon

Anthropic

DeepSeek

Google

Kimi

KwaiKAT

Meta

MiniMax

Mistral

NVIDIA

OpenAI

ServiceNow

xAI

Z AI

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Context Window

Context Window: Tokens Limit; Higher is better

+ Add model from specific provider

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Intelligence vs. Context Window

Artificial Analysis Intelligence Index; Context Window: Tokens Limit

+ Add model from specific provider

Most attractive quadrant

Alibaba

Allen Institute for AI

Amazon

Anthropic

DeepSeek

Google

Kimi

KwaiKAT

Meta

MiniMax

Mistral

NVIDIA

OpenAI

ServiceNow

xAI

Z AI

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Output Speed

Output Tokens per Second; Higher is better

+ Add model from specific provider

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Output Speed by Input Token Count (Context Length)

Output Tokens per Second; Higher is better

+ Add model from specific provider

Medium_coding

Vision_single_image

100 input tokens

1k input tokens

10k input tokens

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Output Speed Variance

Output Tokens per Second; Results by percentile; Higher is better

+ Add model from specific provider

Median; other points represent Min, 25th, 75th percentiles and Max respectively

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Output Speed, Over Time

Output Tokens per Second; Higher is better

+ Add model from specific provider

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Latency: Time To First Answer Token

Seconds to First Answer Token Received; Accounts for Reasoning Model 'Thinking' time

+ Add model from specific provider

Input processing

Thinking (reasoning models, when applicable)

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Latency: Time To First Token

Seconds to First Token Received; Lower is better

+ Add model from specific provider

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Time to First Token by Input Token Count (Context Length)

Seconds to First Token Received; Lower is better

+ Add model from specific provider

Medium_coding

Vision_single_image

100 input tokens

1k input tokens

10k input tokens

Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Time to First Token Variance

Seconds to First Token Received; Results by percentile; Lower is better

+ Add model from specific provider

Median; other points represent Min, 25th, 75th percentiles and Max respectively

Time to First Token, Over Time

Seconds to First Token Received; Lower median is better

+ Add model from specific provider

Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

End-to-End Response Time

Seconds to Output 500 Tokens, including reasoning model 'thinking' time; Lower is better

+ Add model from specific provider

'Thinking' time (reasoning models)

Input processing time

Outputting time

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

End-to-End Response Time by Input Token Count (Context Length)

Seconds to Output 500 Tokens, including reasoning model 'thinking' time; Lower is better

+ Add model from specific provider

Medium_coding

Vision_single_image

100 input tokens

1k input tokens

10k input tokens

Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.

Seconds to receive a 500 token response considering input processing time, 'thinking' time of reasoning models, and output speed.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

End-to-End Response Time, Over Time

Seconds to Output 500 Tokens, including reasoning model 'thinking' time; Lower is better

+ Add model from specific provider

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference

+ Add model from specific provider

Active Parameters

Passive Parameters

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

Intelligence vs. Active Parameters

Active Parameters at Inference Time; Artificial Analysis Intelligence Index

+ Add model from specific provider

Most attractive quadrant

Alibaba

Allen Institute for AI

DeepSeek

Kimi

Meta

MiniMax

Mistral

NVIDIA

OpenAI

ServiceNow

Z AI

Intelligence vs. Total Parameters

Artificial Analysis Intelligence Index; Size in Parameters (Billions)

+ Add model from specific provider

Most attractive quadrant

Alibaba

Allen Institute for AI

DeepSeek

Kimi

Meta

MiniMax

Mistral

NVIDIA

OpenAI

ServiceNow

Z AI

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

Nous Research
Hermes 4 - Llama-3.1 70B (Non-reasoning)	Nous Research	Open	128k
Hermes 4 - Llama-3.1 405B (Non-reasoning)	Nous Research	Open	128k
Hermes 4 - Llama-3.1 405B (Reasoning)	Nous Research	Open	128k
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)	Nous Research	Open	32k
Hermes 4 - Llama-3.1 70B (Reasoning)	Nous Research	Open	128k
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)	Nous Research	Open	128k
Hermes 3 - Llama-3.1 70B	Nous Research	Open	128k

Deep Cogito
Cogito v2.1 (Reasoning)	Deep Cogito	Open	128k

xAI
Grok-1	xAI	Open	8k
Grok 4	xAI	Proprietary	256k
Grok 4 Fast (Reasoning)	xAI	Proprietary	2m
Grok 4 Fast (Non-reasoning)	xAI	Proprietary	2m
Grok 4.1 Fast (Reasoning)	xAI	Proprietary	2m
Grok 3 mini Reasoning (high)	xAI	Proprietary	1m
Grok Code Fast 1	xAI	Proprietary	256k
Grok 4.1 Fast (Non-reasoning)	xAI	Proprietary	2m
Grok Beta	xAI	Proprietary	128k
Grok 3 Reasoning Beta	xAI	Proprietary	1m
Grok 3	xAI	Proprietary	1m
Grok 2 (Dec '24)	xAI	Open	131k

Meta
Llama 3.3 Instruct 70B	Meta	Open	128k
Llama 3.1 Instruct 405B	Meta	Open	128k
Llama 3.2 Instruct 90B (Vision)	Meta	Open	128k
Llama 3.2 Instruct 11B (Vision)	Meta	Open	128k
Llama 4 Maverick	Meta	Open	1m
Llama 4 Scout	Meta	Open	10m
Llama 65B	Meta	Open	2k
Llama 3.1 Instruct 70B	Meta	Open	128k
Llama 3.1 Instruct 8B	Meta	Open	128k
Llama 3.2 Instruct 3B	Meta	Open	128k
Llama 3 Instruct 70B	Meta	Open	8k
Llama 3 Instruct 8B	Meta	Open	8k
Llama 3.2 Instruct 1B	Meta	Open	128k
Llama 2 Chat 7B	Meta	Open	4k
Llama 2 Chat 70B	Meta	Open	4k
Llama 2 Chat 13B	Meta	Open	4k

Google
Gemma 3 270M	Google	Open	32k
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)	Google	Proprietary	1m
Gemma 3 12B Instruct	Google	Open	128k
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)	Google	Proprietary	1m
Gemma 3 27B Instruct	Google	Open	128k
Gemma 3 4B Instruct	Google	Open	128k
Gemma 3n E2B Instruct	Google	Open	32k
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)	Google	Proprietary	1m
Gemma 3n E4B Instruct	Google	Open	32k
Gemma 3 1B Instruct	Google	Open	32k
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)	Google	Proprietary	1m
Gemini 2.5 Pro	Google	Proprietary	1m
Gemini 3 Pro Preview (high)	Google	Proprietary	1m
Gemini 3 Pro Preview (low)	Google	Proprietary	1m
Gemini 2.0 Pro Experimental (Feb '25)	Google	Proprietary	2m
Gemini 2.0 Flash (experimental)	Google	Proprietary	1m
Gemini 1.5 Pro (Sep '24)	Google	Proprietary	2m
Gemini 2.0 Flash-Lite (Preview)	Google	Proprietary	1m
Gemini 2.0 Flash (Feb '25)	Google	Proprietary	1m
Gemini 1.5 Flash (Sep '24)	Google	Proprietary	1m
Gemini 1.5 Flash-8B	Google	Proprietary	1m
Gemini 2.5 Flash (Reasoning)	Google	Proprietary	1m
Gemini 1.0 Ultra	Google	Proprietary	33k
Gemini 2.5 Flash Preview (Non-reasoning)	Google	Proprietary	1m
Gemini 2.5 Flash Preview (Reasoning)	Google	Proprietary	1m
Gemini 1.0 Pro	Google	Proprietary	33k
Gemini 2.5 Flash (Non-reasoning)	Google	Proprietary	1m
Gemini 1.5 Pro (May '24)	Google	Proprietary	2m
Gemini 2.0 Flash Thinking Experimental (Dec '24)	Google	Proprietary	2m
Gemini 2.5 Flash-Lite (Non-reasoning)	Google	Proprietary	1m
Gemini 2.5 Pro Preview (May' 25)	Google	Proprietary	1m
Gemini 2.0 Flash-Lite (Feb '25)	Google	Proprietary	1m
Gemini 1.5 Flash (May '24)	Google	Proprietary	1m
PALM-2	Google	Proprietary	8k
Gemini 2.0 Flash Thinking Experimental (Jan '25)	Google	Proprietary	1m
Gemini 2.5 Flash-Lite (Reasoning)	Google	Proprietary	1m
Gemma 3n E4B Instruct Preview (May '25)	Google	Open	32k
Gemini 2.5 Pro Preview (Mar' 25)	Google	Proprietary	1m

Anthropic
Claude 4.5 Sonnet (Reasoning)	Anthropic	Proprietary	1m
Claude Opus 4.5 (Reasoning)	Anthropic	Proprietary	200k
Claude 4.5 Sonnet (Non-reasoning)	Anthropic	Proprietary	1m
Claude 4.5 Haiku (Reasoning)	Anthropic	Proprietary	200k
Claude Opus 4.5 (Non-reasoning)	Anthropic	Proprietary	200k
Claude 4.5 Haiku (Non-reasoning)	Anthropic	Proprietary	200k
Claude 3.5 Sonnet (Oct '24)	Anthropic	Proprietary	200k
Claude 3.5 Sonnet (June '24)	Anthropic	Proprietary	200k
Claude 3 Opus	Anthropic	Proprietary	200k
Claude 3.5 Haiku	Anthropic	Proprietary	200k
Claude 3 Sonnet	Anthropic	Proprietary	200k
Claude 3 Haiku	Anthropic	Proprietary	200k
Claude Instant	Anthropic	Proprietary	100k
Claude 4 Sonnet (Reasoning)	Anthropic	Proprietary	1m
Claude 3.7 Sonnet (Reasoning)	Anthropic	Proprietary	200k
Claude 4.1 Opus (Non-reasoning)	Anthropic	Proprietary	200k
Claude 3.7 Sonnet (Non-reasoning)	Anthropic	Proprietary	200k
Claude 2.0	Anthropic	Proprietary	100k
Claude 4 Opus (Reasoning)	Anthropic	Proprietary	200k
Claude 4.1 Opus (Reasoning)	Anthropic	Proprietary	200k
Claude 4 Opus (Non-reasoning)	Anthropic	Proprietary	200k
Claude 4 Sonnet (Non-reasoning)	Anthropic	Proprietary	1m
Claude 2.1	Anthropic	Proprietary	200k

Mistral
Devstral Small (Jul '25)	Mistral	Open	256k
Magistral Medium 1.2	Mistral	Proprietary	128k
Mistral Medium 3.1	Mistral	Proprietary	128k
Ministral 8B (Dec '25)	Mistral	Open	256k
Devstral Small 2	Mistral	Open	256k
Ministral 3B (Dec '25)	Mistral	Open	256k
Magistral Small 1.2	Mistral	Open	128k
Devstral 2	Mistral	Open	256k
Mistral Small 3.2	Mistral	Open	128k
Ministral 14B (Dec '25)	Mistral	Open	256k
Devstral Medium	Mistral	Proprietary	256k
Mistral Large 3	Mistral	Open	256k
Mistral Large 2 (Nov '24)	Mistral	Open	128k
Mistral Large 2 (Jul '24)	Mistral	Open	128k
Pixtral Large	Mistral	Open	128k
Mistral Small 3	Mistral	Open	32k
Mistral Small (Sep '24)	Mistral	Open	33k
Mixtral 8x22B Instruct	Mistral	Open	65k
Mistral Small (Feb '24)	Mistral	Proprietary	33k
Mistral Large (Feb '24)	Mistral	Proprietary	33k
Mixtral 8x7B Instruct	Mistral	Open	33k
Mistral 7B Instruct	Mistral	Open	8k
Mistral Small 3.1	Mistral	Open	128k
Mistral Medium 3	Mistral	Proprietary	128k
Magistral Small 1	Mistral	Open	40k
Magistral Medium 1	Mistral	Proprietary	40k
Mistral Medium	Mistral	Proprietary	33k
Devstral Small (May '25)	Mistral	Open	256k
Mistral Saba	Mistral	Proprietary	32k

DeepSeek
DeepSeek R1 Distill Llama 70B	DeepSeek	Open	128k
DeepSeek R1 0528 (May '25)	DeepSeek	Open	128k
DeepSeek V3.2 (Non-reasoning)	DeepSeek	Open	128k
DeepSeek V3.1 Terminus (Non-reasoning)	DeepSeek	Open	128k
DeepSeek-OCR	DeepSeek	Open	8k
DeepSeek R1 0528 Qwen3 8B	DeepSeek	Open	33k
DeepSeek V3.1 Terminus (Reasoning)	DeepSeek	Open	128k
DeepSeek V3.2 (Reasoning)	DeepSeek	Open	128k
DeepSeek V3.2 Speciale	DeepSeek	Open	128k
DeepSeek R1 Distill Qwen 32B	DeepSeek	Open	128k
DeepSeek V3 (Dec '24)	DeepSeek	Open	128k
DeepSeek R1 Distill Qwen 14B	DeepSeek	Open	128k
DeepSeek-V2.5 (Dec '24)	DeepSeek	Open	128k
DeepSeek-Coder-V2	DeepSeek	Open	128k
DeepSeek R1 Distill Llama 8B	DeepSeek	Open	128k
DeepSeek LLM 67B Chat (V1)	DeepSeek	Open	4k
DeepSeek R1 Distill Qwen 1.5B	DeepSeek	Open	128k
DeepSeek V3 0324	DeepSeek	Open	128k
DeepSeek R1 (Jan '25)	DeepSeek	Open	128k
DeepSeek-V2-Chat	DeepSeek	Open	128k
DeepSeek V3.1 (Non-reasoning)	DeepSeek	Open	128k
DeepSeek V3.1 (Reasoning)	DeepSeek	Open	128k
DeepSeek V3.2 Exp (Non-reasoning)	DeepSeek	Open	128k
DeepSeek-V2.5	DeepSeek	Open	128k
DeepSeek Coder V2 Lite Instruct	DeepSeek	Open	128k
DeepSeek V3.2 Exp (Reasoning)	DeepSeek	Open	128k

Perplexity
R1 1776	Perplexity	Open	128k
Sonar Pro	Perplexity	Proprietary	200k
Sonar Reasoning	Perplexity	Proprietary	127k
Sonar	Perplexity	Proprietary	127k
Sonar Reasoning Pro	Perplexity	Proprietary	127k

Amazon
Nova Micro	Amazon	Proprietary	130k
Nova 2.0 Omni (Non-reasoning)	Amazon	Proprietary	1m
Nova 2.0 Lite (Non-reasoning)	Amazon	Proprietary	1m
Nova 2.0 Lite (low)	Amazon	Proprietary	1m
Nova 2.0 Omni (low)	Amazon	Proprietary	1m
Nova 2.0 Pro Preview (low)	Amazon	Proprietary	256k
Nova 2.0 Lite (medium)	Amazon	Proprietary	1m
Nova Premier	Amazon	Proprietary	1m
Nova 2.0 Omni (medium)	Amazon	Proprietary	1m
Nova 2.0 Pro Preview (Non-reasoning)	Amazon	Proprietary	256k
Nova 2.0 Pro Preview (medium)	Amazon	Proprietary	256k
Nova Pro	Amazon	Proprietary	300k
Nova Lite	Amazon	Proprietary	300k

Microsoft Azure
Phi-4	Microsoft Azure	Open	16k
Phi-4 Mini Instruct	Microsoft Azure	Open	128k
Phi-4 Multimodal Instruct	Microsoft Azure	Open	128k
Phi-3 Medium Instruct 14B	Microsoft Azure	Open	128k
Phi-3 Mini Instruct 3.8B	Microsoft Azure	Open	4k

Liquid AI
LFM2 8B A1B	Liquid AI	Open	33k
LFM2 1.2B	Liquid AI	Open	33k
LFM2 2.6B	Liquid AI	Open	33k
LFM 40B	Liquid AI	Proprietary	32k

Upstage
Solar Pro 2 (Non-reasoning)	Upstage	Proprietary	66k
Solar Pro 2 (Reasoning)	Upstage	Proprietary	66k
Solar Mini	Upstage	Open	4k
Solar Pro 2 (Preview) (Reasoning)	Upstage	Proprietary	64k
Solar Pro 2 (Preview) (Non-reasoning)	Upstage	Proprietary	64k

MiniMax
MiniMax-M2	MiniMax	Open	205k
MiniMax M1 40k	MiniMax	Open	1m
MiniMax M1 80k	MiniMax	Open	1m

NVIDIA
Llama 3.1 Nemotron Instruct 70B	NVIDIA	Open	128k
NVIDIA Nemotron Nano 9B V2 (Reasoning)	NVIDIA	Open	131k
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)	NVIDIA	Open	128k
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)	NVIDIA	Open	131k
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)	NVIDIA	Open	128k
Llama 3.3 Nemotron Super 49B v1 (Reasoning)	NVIDIA	Open	128k
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)	NVIDIA	Open	128k
Llama Nemotron Super 49B v1.5 (Non-reasoning)	NVIDIA	Open	128k
Llama Nemotron Super 49B v1.5 (Reasoning)	NVIDIA	Open	128k
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)	NVIDIA	Open	128k
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)	NVIDIA	Open	128k

Kimi
Kimi K2 Thinking	Kimi	Open	256k
Kimi Linear 48B A3B Instruct	Kimi	Open	1m
Kimi K2 0905	Kimi	Open	256k
Kimi K2	Kimi	Open	128k

Allen Institute for AI
Molmo 7B-D	Allen Institute for AI	Open	4k
OLMo 3 7B Instruct	Allen Institute for AI	Open	66k
OLMo 3 32B Think	Allen Institute for AI	Open	66k
OLMo 3 7B Think	Allen Institute for AI	Open	66k
Llama 3.1 Tulu3 405B	Allen Institute for AI	Open	128k
OLMo 2 32B	Allen Institute for AI	Open	4k
OLMo 2 7B	Allen Institute for AI	Open	4k

IBM
Granite 4.0 H Small	IBM	Open	128k
Granite 4.0 350M	IBM	Open	33k
Granite 4.0 H 350M	IBM	Open	33k
Granite 4.0 H 1B	IBM	Open	128k
Granite 4.0 1B	IBM	Open	128k
Granite 4.0 Micro	IBM	Open	128k
Granite 3.3 8B (Non-reasoning)	IBM	Open	128k

Reka AI
Reka Flash 3	Reka AI	Open	128k
Reka Flash (Sep '24)	Reka AI	Proprietary	128k

LG AI Research
Exaone 4.0 1.2B (Reasoning)	LG AI Research	Open	64k
Exaone 4.0 1.2B (Non-reasoning)	LG AI Research	Open	64k
EXAONE 4.0 32B (Reasoning)	LG AI Research	Open	131k
EXAONE 4.0 32B (Non-reasoning)	LG AI Research	Open	131k

Baidu
ERNIE 4.5 300B A47B	Baidu	Open	131k
ERNIE 5.0 Thinking Preview	Baidu	Proprietary	128k

Motif Technologies
Motif-2-12.7B-Reasoning	Motif Technologies	Proprietary	128k

Comparison of Models: Intelligence, Performance & Price Analysis

Highlights

Navigation

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Artificial Analysis Coding Index

Artificial Analysis Coding Index

Artificial Analysis Agentic Index

Artificial Analysis Agentic Index

Artificial Analysis Intelligence Index by Open Weights vs Proprietary

Artificial Analysis Intelligence Index

Open Weights

Artificial Analysis Intelligence Index by Model Type

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Artificial Analysis Omniscience

AA-Omniscience Index

AA-Omniscience Index

AA-Omniscience Accuracy

AA-Omniscience Accuracy

AA-Omniscience Hallucination Rate

AA-Omniscience Hallucination Rate

Openness

Artificial Analysis Openness Index: Results

Artificial Analysis Openness Index: Components

Artificial Analysis Openness Index vs. Artificial Analysis Intelligence Index

Intelligence Index Comparisons

Intelligence vs. Price

Price-Quality Variance

Artificial Analysis Intelligence Index

Price

Model Performance Representation

Intelligence vs. Output Speed

Intelligence vs Speed Trade-off

Artificial Analysis Intelligence Index

Output Speed

Model Performance Representation

Intelligence vs. End-to-End Response Time

Artificial Analysis Intelligence Index

End-to-End Response Time

Model Performance Representation

Intelligence Index Token Use & Cost

Output Tokens Used to Run Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index Tokens Use

Intelligence vs. Output Tokens Used in Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index Tokens Use

Artificial Analysis Intelligence Index

Cost to Run Artificial Analysis Intelligence Index

Cost to Run Artificial Analysis Intelligence Index

Intelligence vs. Cost to Run Artificial Analysis Intelligence Index

Cost to Run Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Context Window

Context Window

Context Window for RAG

Context window

Intelligence vs. Context Window

Artificial Analysis Intelligence Index

Context window

Pricing

Pricing: Input and Output Prices

Input Price

Model Performance Representation

Pricing: Cached Input Prompts

Prompt Caching

Input Price

Cache Write

Cache Hit

Cache Storage per Hour

Output Price

Pricing: Image Input Pricing

Price per 1k 1MP images

Model Performance Representation

Intelligence vs. Price (Log Scale)

Price-Quality Variance

Artificial Analysis Intelligence Index

Price

Z AI
GLM-4.6 (Non-reasoning)	Z AI	Open	200k
GLM-4.5-Air	Z AI	Open	128k
GLM-4.6 (Reasoning)	Z AI	Open	200k
GLM-4.6V (Reasoning)	Z AI	Open	128k
GLM-4.6V (Non-reasoning)	Z AI	Open	128k
GLM-4.5V (Non-reasoning)	Z AI	Open	64k
GLM-4.5V (Reasoning)	Z AI	Open	64k
GLM-4.5 (Reasoning)	Z AI	Open	128k

Cohere
Command A	Cohere	Open	256k
Command-R+ (Apr '24)	Cohere	Open	128k
Command-R (Mar '24)	Cohere	Open	128k

ServiceNow
Apriel-v1.6-15B-Thinker	ServiceNow	Open	128k
Apriel-v1.5-15B-Thinker	ServiceNow	Open	128k

AI21 Labs
Jamba Reasoning 3B	AI21 Labs	Open	262k
Jamba 1.7 Large	AI21 Labs	Open	256k
Jamba 1.7 Mini	AI21 Labs	Open	258k
Jamba 1.5 Large	AI21 Labs	Open	256k
Jamba 1.6 Large	AI21 Labs	Open	256k
Jamba 1.6 Mini	AI21 Labs	Open	256k
Jamba 1.5 Mini	AI21 Labs	Open	256k

Alibaba
Qwen3 4B 2507 (Reasoning)	Alibaba	Open	262k
Qwen3 Coder 480B A35B Instruct	Alibaba	Open	262k
Qwen3 VL 4B (Reasoning)	Alibaba	Open	256k
Qwen3 VL 235B A22B Instruct	Alibaba	Open	262k
Qwen3 Coder 30B A3B Instruct	Alibaba	Open	262k
Qwen3 VL 235B A22B (Reasoning)	Alibaba	Open	262k
Qwen3 235B A22B 2507 (Reasoning)	Alibaba	Open	256k
Qwen3 Omni 30B A3B (Reasoning)	Alibaba	Open	66k
Qwen3 Omni 30B A3B Instruct	Alibaba	Open	66k
Qwen3 Max Thinking	Alibaba	Proprietary	262k
Qwen3 235B A22B 2507 Instruct	Alibaba	Open	256k
Qwen3 VL 30B A3B Instruct	Alibaba	Open	256k
Qwen3 VL 8B (Reasoning)	Alibaba	Open	256k
Qwen3 VL 4B Instruct	Alibaba	Open	256k
Qwen3 Next 80B A3B (Reasoning)	Alibaba	Open	262k
Qwen3 VL 30B A3B (Reasoning)	Alibaba	Open	256k
Qwen3 30B A3B 2507 (Reasoning)	Alibaba	Open	262k
Qwen3 30B A3B 2507 Instruct	Alibaba	Open	262k
Qwen3 Next 80B A3B Instruct	Alibaba	Open	262k
Qwen Chat 14B	Alibaba	Open	8k
Qwen3 VL 8B Instruct	Alibaba	Open	256k
Qwen3 4B 2507 Instruct	Alibaba	Open	262k
Qwen3 VL 32B Instruct	Alibaba	Open	256k
Qwen3 Max	Alibaba	Proprietary	262k
Qwen3 VL 32B (Reasoning)	Alibaba	Open	256k
Qwen2.5 Max	Alibaba	Proprietary	32k
Qwen2.5 Instruct 72B	Alibaba	Open	131k
Qwen2.5 Coder Instruct 32B	Alibaba	Open	131k
Qwen2.5 Turbo	Alibaba	Proprietary	1m
Qwen2 Instruct 72B	Alibaba	Open	131k
Qwen3 32B (Reasoning)	Alibaba	Open	33k
Qwen3 235B A22B (Reasoning)	Alibaba	Open	33k
QwQ 32B	Alibaba	Open	131k
Qwen3 30B A3B (Reasoning)	Alibaba	Open	33k
Qwen3 32B (Non-reasoning)	Alibaba	Open	33k
Qwen Chat 72B	Alibaba	Open	34k
Qwen3 235B A22B (Non-reasoning)	Alibaba	Open	33k
Qwen3 14B (Reasoning)	Alibaba	Open	33k
QwQ 32B-Preview	Alibaba	Open	33k
Qwen3 1.7B (Non-reasoning)	Alibaba	Open	32k
Qwen3 8B (Non-reasoning)	Alibaba	Open	33k
Qwen3 4B (Reasoning)	Alibaba	Open	32k
Qwen3 30B A3B (Non-reasoning)	Alibaba	Open	33k
Qwen3 1.7B (Reasoning)	Alibaba	Open	32k
Qwen2.5 Instruct 32B	Alibaba	Open	128k
Qwen3 0.6B (Non-reasoning)	Alibaba	Open	32k
Qwen3 8B (Reasoning)	Alibaba	Open	131k
Qwen2.5 Coder Instruct 7B	Alibaba	Open	131k
Qwen3 Max (Preview)	Alibaba	Proprietary	262k
Qwen3 14B (Non-reasoning)	Alibaba	Open	33k
Qwen3 4B (Non-reasoning)	Alibaba	Open	32k
Qwen3 0.6B (Reasoning)	Alibaba	Open	32k
Qwen1.5 Chat 110B	Alibaba	Open	32k

InclusionAI
Ling-1T	InclusionAI	Open	128k
Ling-mini-2.0	InclusionAI	Open	131k
Ring-1T	InclusionAI	Open	128k
Ring-flash-2.0	InclusionAI	Open	128k
Ling-flash-2.0	InclusionAI	Open	128k

ByteDance Seed
Doubao Seed Code	ByteDance Seed	Proprietary	256k
Seed-OSS-36B-Instruct	ByteDance Seed	Open	512k