Unabhängige Analyse von KI

Die KI-Landschaft verstehen und das beste Modell und den besten Anbieter für den eigenen Anwendungsfall auswählen

Highlights

Intelligenz

Artificial Analysis Intelligence Index · Higher is better

Geschwindigkeit

Output tokens per second · Higher is better

Kosten pro Aufgabe

Weighted average cost (USD) per Intelligence Index task · Lower is better

Personalisierte Modellempfehlung

Personalisierte Empfehlungen anhand der eigenen Prioritäten für Intelligenz, Geschwindigkeit und Kosten erhalten

Agenten für allgemeine Aufgaben, Programmierung, Kundenservice und mehr entdecken

KI-Agenten nach Fähigkeiten, Preisen und Plattformunterstützung vergleichen

Premium-Tarife entdecken

Auf erweiterte Benchmark-Daten, individuelle Visualisierungen, Branchenberichte und mehr zugreifen

Änderungsprotokoll
Neue Sprachmodellevaluation · 3. Aug.
G9v3-39A5BG9v3-39A5B
Neuer Artikel veröffentlicht · 31. Juli
DeepSeek V4 Flash 0731 scores 50 on the Artificial Analysis Intelligence Index, 10 points above previous DeepSeek V4 Flash
Neue Sprachmodellevaluation · 31. Juli
Celeris-1Celeris-1
Neue Sprachmodellevaluation · 31. Juli
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
Neuer Artikel veröffentlicht · 30. Juli
Inkling Small lands within a point of Inkling on the Artificial Analysis Intelligence Index with less than a third of the parameters
Methodik aktualisiert · 30. Juli
Artificial AnalysisWe have updated our Cost per Task methodology, resulting in slight absolute increases in cost estimates but with minimal impact on relative positioning.
Neue Sprachmodellevaluation · 30. Juli
Kimi K3 (low)Kimi K3 (low)
Neue Sprachmodellevaluation · 30. Juli
Inkling SmallInkling Small
Neuer Artikel veröffentlicht · 29. Juli
Agnes AI releases Agnes 2.5 Pro Alpha
Neuer Artikel veröffentlicht · 24. Juli
Claude Opus 5: the new leader in agentic knowledge work
Neuer Artikel veröffentlicht · 24. Juli
Opus 5: Fable 5 level intelligence at a lower cost per task
Neue Sprachmodellevaluation · 24. Juli
Claude Opus 5 (Adaptive Reasoning, Low Effort)Claude Opus 5 (Adaptive Reasoning, Low Effort)
Neue Sprachmodellevaluation · 24. Juli
Claude Opus 5 (Adaptive Reasoning, Medium Effort)Claude Opus 5 (Adaptive Reasoning, Medium Effort)
Neue Sprachmodellevaluation · 24. Juli
Claude Opus 5 (Adaptive Reasoning, High Effort)Claude Opus 5 (Adaptive Reasoning, High Effort)
Neue Sprachmodellevaluation · 24. Juli
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
Neue Sprachmodellevaluation · 24. Juli
Claude Opus 5 (Adaptive Reasoning, Max Effort)Claude Opus 5 (Adaptive Reasoning, Max Effort)
Neue Sprachmodellevaluation · 23. Juli
Agnes 2.5 Pro AlphaAgnes 2.5 Pro Alpha
Neuer Artikel veröffentlicht · 22. Juli
How Thinking Machines Lab’s Inkling performs on agentic knowledge work
Neue Sprachmodellevaluation · 22. Juli
G9v3-3BG9v3-3B
Neuer Artikel veröffentlicht · 21. Juli
Kimi K3: second only to Fable 5 on AA-BriefcaseMehr anzeigen

Intelligenz

Intelligenz führender KI-Modelle auf Grundlage unserer unabhängigen Evaluationen

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. 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).

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligenz von Frontier-Sprachmodellen im Zeitverlauf

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Coding Agent Index

Leistung, Kosten und Ausführungszeit führender Programmieragenten bei durchgängigen Aufgaben der Softwareentwicklung

Artificial Analysis Coding Agent Index

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

Bild und Video

Führende Modelle aus den Bestenlisten unserer Image Arena und Video Arena mit 95-%-Konfidenzintervallen

Text-zu-Bild-Bestenliste

Elo-Werte aus blinden Präferenzabstimmungen in unserer Image Arena. Hier die vollständige Bestenliste ansehen.

Sprache

Führende Modelle aus unserer Text to Speech Arena sowie unseren Speech-to-Text- und Speech-to-Speech-Evaluationen

Text to Speech Arena Leaderboard

Elo scores from blind preference votes in our Text to Speech Arena · See the full leaderboard here.

Relative Elo score of the models as determined by responses from users in Artificial Analysis' Speech Arena. Some models may not be shown due to not yet having enough votes.

FähigkeitsindizesUpdated

Mehr anzeigen

Misst die Leistung von Modellen bei bestimmten Fähigkeiten und in bestimmten Branchen

Artificial Analysis Agentic Index

Measures performance in agentic workflows, focusing on behaviors like tool use, planning, autonomy, and complex problem solving.
Reasoning models are indicated by a lightbulb icon

Benchmarks

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
GDPval-AA v2

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

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

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

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

AA-Briefcase

AA-Briefcase ist eine agentische Frontier-Evaluation für Wissensarbeit über lange Zeithorizonte. Agenten werden mit realistischen Geschäftsabläufen getestet, die Ergebnisse wie Tabellen, Präsentationen und Memos erfordern

AA-Briefcase Elo

AA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better
Reasoning models are indicated by a lightbulb icon

AA-Briefcase Elo is a combined metric that aggregates analytical quality Elo, presentation Elo, and rubric pass rate, with rubric performance converted into Elo via synthetic head-to-head matches. Elo and 95% confidence interval bounds are clamped at 0.

AA-Omniscience

AA-Omniscience ist ein Benchmark für Wissen und Halluzinationen, der Genauigkeit belohnt, falsche Vermutungen bestraft und umfassend zeigt, welche Modelle in verschiedenen Bereichen sachlich zuverlässige Ausgaben erzeugen

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.
Reasoning models are indicated by a lightbulb icon

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.

GDPval-AA v2

GDPval-AA v2 evaluiert KI-Modelle anhand realer, wirtschaftlich wertvoller Aufgaben aus zahlreichen Berufen

GDPval-AA v2 Leaderboard

Elo rating for performance on real-world work tasks · Anchored to a human baseline of 1,000 · Higher is better
Human Baseline (1,000)
Reasoning models are indicated by a lightbulb icon

Openness Index

Der Artificial Analysis Openness Index bewertet anhand ihrer Verfügbarkeit und Transparenz in verschiedenen Komponenten, wie „offen“ Modelle sind.

Artificial Analysis Openness Index: Components

Openness Index underlying score contribution by components, up to a maximum of 18 (higher is more open)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Openness Index vs. Artificial Analysis Intelligence Index

Most attractive quadrant
Pareto line

Ausgabetokens

Ausgabetokens führender KI-Modelle auf Grundlage unserer unabhängigen Evaluationen

Output Tokens per Intelligence Index Task

Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index
Reasoning models are indicated by a lightbulb icon

The number of tokens required per Intelligence Index task. This is calculated by multiplying the output tokens per eval by the relative weights of each benchmark in the Intelligence Index, then dividing by task count (excluding repeats).

Kosten

Preise und reale Kosten führender KI-Modelle auf Grundlage unserer unabhängigen Evaluationen

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index
Reasoning models are indicated by a lightbulb icon

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)
Reasoning models are indicated by a lightbulb icon

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Geschwindigkeit und Latenz

Leistungsvergleich von Erstanbieter-APIs

Output Speed

Output tokens per second · Higher is better
Reasoning models are indicated by a lightbulb icon

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).

Time per Intelligence Index Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better
Reasoning models are indicated by a lightbulb icon

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Anbieter

Endpoint Accuracy Index: gpt-oss-120b (high)

v1.0 · Composite of BFCL v4-500, HLE-250 and AA-LCR-25 run against each provider endpoint · Percentage of the reference endpoint, with 95% confidence interval · Higher is better

Composite measure of how much of a model's accuracy a given provider endpoint preserves, from re-running BFCL v4-500, HLE-250 and AA-LCR-25 against that endpoint. Where a self-hosted reference endpoint exists, scores are expressed as a percentage of that reference (100 = matches reference); lower scores indicate accuracy lost to quantisation, sampling defaults, or other endpoint-side configuration. Scores are point-in-time snapshots. Methodology.

Output Speed vs. Price: gpt-oss-120b (high)

Output tokens per second · USD per 1M tokens (blended) · 10,000 input tokens
Most attractive quadrant
Pareto line
Reasoning models are indicated by a lightbulb icon

Smaller, emerging providers are offering high output speed and at competitive prices.

Preise (Cache-Treffer, Eingabe und Ausgabe): gpt-oss-120b (high)

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Output Speed: gpt-oss-120b (high)

Output speed: output tokens per second · 10,000 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).

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).