AI Model & API Providers Analysis | Artificial Analysis

Source: original

Artificial Analysis

Artificial Analysis

K

Independent analysis of AI

Understand the AI landscape to choose the best model and provider for your use case

AnnouncementA new look for Artificial AnalysisSame mission, new lookLaunchCoding Agent BenchmarksIntroducing the Artificial Analysis Coding Agent Benchmarks

Highlights

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Updated

Price

USD per 1M tokens (blended) · Lower is better

Personalized model recommenderGet personalized recommendations based on your priorities for intelligence, speed, and costExplore agents for general work, coding, customer support, and moreCompare AI agents across capabilities, pricing, and platform supportWhat is the Artificial Analysis Intelligence Index?Learn about the Artificial Analysis Intelligence Index and how it is calculated

Changelog

New language model evaluation · 10 Jun

Gemma 4 12B (Non-reasoning)

New article published · 9 Jun

Claude Fable 5 Launches at #1 on the Artificial Analysis Intelligence Index

New article published · 9 Jun

Claude Fable 5: the first public Mythos-class model

New article published · 9 Jun

North Mini Code: Cohere's small coding-focused MoE model

New language model evaluation · 9 Jun

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

New language model evaluation · 9 Jun

North Mini Code

New article published · 8 Jun

MiniMax-M3: Leading open weights model, once the weights are released

New language model evaluation · 8 Jun

LFM2.5-8B-A1B

New language model evaluation · 7 Jun

Gemma 4 12B (Reasoning)

New article published · 4 Jun

NVIDIA Nemotron 3 Ultra released: fast, intelligent, and open

New language model evaluation · 4 Jun

MiniCPM5-1B (Reasoning)

New language model evaluation · 4 Jun

Nemotron 3 Ultra 550B A55B (Reasoning)

New video model · 4 Jun

grok-imagine-video-1.5-preview

New article published · 3 Jun

Fun-Realtime-TTS: New Text to Speech model topping Artificial Analysis leaderboard

New language model evaluation · 3 Jun

MiniMax-M3

New article published · 2 Jun

MAI-Transcribe-1.5: New Speech to Text model leading the accuracy-speed Pareto frontier

New language model evaluation · 2 Jun

Qwen3.7 Plus

New article published · 1 Jun

AA-WER Streaming: New Speech to Text Streaming Benchmark

New language model evaluation · 1 Jun

Step 3.7 Flash

New image model · 1 Jun

Krea 2 LargeSee more

IntelligenceArtificial Analysis Coding Agent IndexImage & Video LeaderboardsIntelligence BreakdownAA-OmniscienceGDPval-AAITBench-AANewArtificial Analysis Openness IndexOutput TokensCost EfficiencySpeed & LatencyPriceUpdatedAPI Provider Performance

Intelligence

Intelligence of leading AI models based on our independent evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.0 incorporates 10 evaluations: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt

28 of 537 models

Add model from specific provider

Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.0 incorporates 10 evaluations: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt

28 of 537 models

Add model from specific provider

ProprietaryOpen WeightsOpen Weights (Commercial Use Restricted)

Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index

Open Weights

Intelligence vs. Cost to Run Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index · Cost to run Intelligence Index

28 of 537 models

Add model from specific provider

Most attractive quadrant

OpenAIGoogleAnthropicMistralDeepSeekxAIAmazonMiniMaxNVIDIAKimiXiaomiAlibaba

Reasoning models are indicated by a lightbulb icon.

Cost to Run Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Frontier Language Model Intelligence, Over Time

Artificial Analysis Intelligence Index v4.0 incorporates 10 evaluations: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt

14 of 51 model creators

OpenAIxAIMetaGoogleAnthropicMistralDeepSeekUpstageMiniMaxKimiAlibabaXiaomiMBZUAI Institute of Foundation ModelsZ AI

Reasoning models are indicated by a lightbulb icon.

Artificial Analysis Intelligence Index

Artificial Analysis Coding Agent Index

Performance, cost, and execution time for leading coding agents on end-to-end software engineering tasks

Explore Artificial Analysis Coding Agent Index

Artificial Analysis Coding Agent Index

Composite average pass@1 across SWE-Bench-Pro-Hard-AA, Terminal-Bench v2, and SWE-Atlas-QnA · Higher is better

Color by

ModelAgent

14 of 21 models

Image & Video Leaderboards

Top models from our Image Arena and Video Arena leaderboards, with 95% confidence intervals

Text to Image Leaderboard

Elo scores from blind preference votes in our Image Arena. See the full leaderboard here.

15 of 128 models

Intelligence Breakdown

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

14 of 16 quality evaluations

28 of 537 models

Add model from specific provider

GDPval-AA

Agentic real-world work tasks, (Elo-500)/2000

Terminal-Bench Hard

Agentic coding & terminal use

𝜏²-Bench Telecom

Agentic tool use

AA-LCR

Long context reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

SciCode

Coding

IFBench

Instruction following

CritPt

Physics reasoning

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon.

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

AA-Omniscience

AA-Omniscience is a knowledge and hallucination benchmark that rewards accuracy, punishes bad guesses and provides a comprehensive view of which models produce factually reliable outputs across different domains

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.

27 of 411 models

Add model from specific provider

Reasoning models are indicated by a lightbulb icon

AA-Omniscience Index

GDPval-AA

GDPval-AA evaluates AI models on real-world, economically valuable tasks across a wide range of occupations

GDPval-AA Leaderboard

Elo scores for agentic performance on real-world work tasks using web and shell access via Stirrup, an open-source harness developed by Artificial Analysis

27 of 385 models

Add model from specific provider

ITBench-AANew

ITBench-AA evaluates AI agents on Kubernetes incident root-cause analysis from offline incident snapshots

ITBench-AA Average precision at full recall

Average precision at full recall on Kubernetes incident root-cause analysis from offline incident snapshots · For Site Reliability Engineering (SRE) tasks

16 of 24 models

Add model from specific provider

Reasoning models are indicated by a lightbulb icon

ITBench-AA Average Precision at Full Recall

Artificial Analysis Openness Index

Artificial Analysis Openness Index assesses how 'open' models are on the basis of their availability and transparency across different components.

Artificial Analysis Openness Index: Components

Openness Index underlying score contribution by components, up to a maximum of 18 (higher is more open)

28 of 537 models

Add model from specific provider

Transparency - Pre-training DataTransparency - Post-training DataTransparency - MethodologyModel Availability

Reasoning models are indicated by a lightbulb icon

Artificial Analysis Openness Index vs. Artificial Analysis Intelligence Index

28 of 537 models

Add model from specific provider

Most attractive quadrant

KimiXiaomiDeepSeekZ AIMiniMaxNVIDIAAlibabaMistralGoogleAnthropicOpenAIMBZUAI Institute of Foundation Models

Output Tokens

Output tokens of leading AI models based on our independent evaluations

Output Tokens Used to Run Artificial Analysis Intelligence Index

Tokens used to run all evaluations in the Artificial Analysis Intelligence Index

28 of 537 models

Add model from specific provider

Answer TokensReasoning Tokens

Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index Output Tokens

Cost Efficiency

Cost of leading AI models based on our independent evaluations

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

28 of 537 models

Add model from specific provider

OutputReasoningInput

Reasoning models are indicated by a lightbulb icon

Cost to Run Artificial Analysis Intelligence Index

Speed & Latency

Comparison of first-party API performance

Output Speed

Output tokens per second · Higher is better

28 of 537 models

Add model from specific provider

Reasoning models are indicated by a lightbulb icon

Output Speed

Model Performance Representation

PriceUpdated

Price of leading AI models based on our independent evaluations

NewHardware BenchmarkingComprehensive benchmarking of GPUs for language model inferenceVideo Arena & LeaderboardCompare leading Text to Video and Image to Video modelsImage Arena & LeaderboardCompare leading Image Generation and Image Editing modelsSpeech Arena & LeaderboardCompare leading Text to Speech models

API Provider Performance