Modellvergleich: Analyse von Intelligenz, Leistung und Preis

Microevals Playground
Vergleich und Analyse von KI-Modellen anhand wichtiger Leistungsmetriken wie Qualität, Preis, Ausgabegeschwindigkeit, Latenz und Kontextfenster. Klicken Sie auf ein Modell, um detaillierte Metriken anzuzeigen. Weitere Informationen, auch zu unserer Methodik, finden Sie in unseren häufig gestellten Fragen.

Intelligenz

Logo von Claude Opus 5 (max) Claude Opus 5 (max) und Logo von Claude Opus 5 (xhigh) Claude Opus 5 (xhigh) sind die intelligentesten Modelle, gefolgt von Logo von Claude Fable 5 (with fallback) Claude Fable 5 (with fallback) und Logo von GPT-5.6 Sol (max) GPT-5.6 Sol (max).

Ausgabegeschwindigkeit (Tokens/s)

Logo von Celeris-1 Celeris-1 (2034 t/s) und Logo von Mercury 2 Mercury 2 (742 t/s) sind die schnellsten Modelle, gefolgt von Logo von LFM2.5-VL-1.6B LFM2.5-VL-1.6B und Logo von Step 3.7 Flash Step 3.7 Flash.

Latenz (Sekunden)

Logo von Gemini 2.5 Flash-Lite Gemini 2.5 Flash-Lite (0.33s) und Logo von Command A+ Command A+ (0.44s) sind die Modelle mit der niedrigsten Latenz, gefolgt von Logo von Gemini 2.5 Flash Gemini 2.5 Flash und Logo von Grok Build 0.1 0616 Grok Build 0.1 0616.

Preis ($ pro Mio. Tokens)

Logo von Devstral 2 Devstral 2 ($0.00) und Logo von North Mini Code North Mini Code ($0.00) sind die günstigsten Modelle, gefolgt von Logo von Gemma 3 4B Gemma 3 4B und Logo von Gemma 3 27B Gemma 3 27B.

Kontextfenster

Logo von Llama 4 Scout Llama 4 Scout (10M) und Logo von Grok 4.20 0309 Grok 4.20 0309 (2M) sind die Modelle mit den größten Kontextfenstern, gefolgt von Logo von Gemini 1.5 Pro (May) Gemini 1.5 Pro (May) und Logo von Grok 4.1 Fast Grok 4.1 Fast.

Wichtigste Ergebnisse

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

Intelligenz

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).

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 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 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.

Openness Index

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)
Reasoning models are indicated by a lightbulb icon

Vergleiche des Intelligence Index

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.

Tokenverbrauch

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

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.

Kontextfenster

Context Window

Context window: tokens limit · Higher is better
Reasoning models are indicated by a lightbulb icon

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).

Geschwindigkeit

Gemessen anhand der Ausgabegeschwindigkeit (Tokens pro Sekunde)

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.

Latenz

Gemessen anhand der Zeit (in Sekunden) bis zum ersten Token

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time
Reasoning models are indicated by a lightbulb icon

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.

Ende-zu-Ende-Antwortzeit

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better
Reasoning models are indicated by a lightbulb icon

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).

Modellgröße (nur Modelle mit offenen Gewichten)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference
Reasoning models are indicated by a lightbulb icon

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.

Häufig gestellte Fragen

Claude Opus 5 (Adaptive Reasoning, Max Effort) führt derzeit den Artificial Analysis Intelligence Index mit einem Wert von 61 an. Insgesamt wurden 175 Modelle bewertet.

Die führenden KI-Modelle nach Intelligence Index sind: 1. Claude Opus 5 (Adaptive Reasoning, Max Effort) (61), 2. Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) (60), 3. Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) (60), 4. GPT-5.6 Sol (max) (59) und 5. Claude Opus 5 (Adaptive Reasoning, High Effort) (59).

Celeris-1 ist mit 2,033.7 Tokens pro Sekunde am schnellsten, gefolgt von Mercury 2 (741.8 Tokens/s) und LFM2.5-VL-1.6B (474.5 Tokens/s).

Nova Micro ist mit $0.03 pro 1 Mio. Tokens (Mischpreis) am günstigsten, gefolgt von Sarvam 30B (high) ($0.03) und Gemma 4 E4B (Non-reasoning) ($0.03).

Gemini 2.5 Flash-Lite (Non-reasoning) hat mit 0.33 s die kürzeste Zeit bis zum ersten Token, gefolgt von Command A+ (0.44 s) und Gemini 2.5 Flash (Non-reasoning) (0.47 s).

Kimi K3 (max) ist mit einem Intelligence-Index-Wert von 57 das am höchsten eingestufte Modell mit offenen Gewichten. Von insgesamt 175 bewerteten Modellen haben 99 Modelle offene Gewichte.

Die führenden KI-Modelle mit offenen Gewichten nach Intelligence Index sind: 1. Kimi K3 (max) (57), 2. GLM-5.2 (max) (51) und 3. DeepSeek V4 Flash 0731 (Reasoning, Max Effort) (50).

Claude Opus 5 (Adaptive Reasoning, Max Effort) führt unter 130 Reasoning-Modellen mit einem Intelligence-Index-Wert von 61. Reasoning-Modelle durchdenken komplexe Probleme ausführlich, bevor sie eine Antwort geben.

Modelle werden in mehreren Dimensionen verglichen, darunter Intelligenz (Qualität), Preis, Ausgabegeschwindigkeit (Tokens pro Sekunde), Latenz (Zeit bis zum ersten Token), Ende-zu-Ende-Antwortzeit und Größe des Kontextfensters. Die Leistungsmetriken werden mit standardisierten Prompts direkt über 591 Modelle gemessen.

Klicken Sie in den Diagrammen auf einen Modellnamen oder eine Zeile, um die zugehörige Seite mit detaillierten Metriken und direkten Vergleichen mit ähnlichen Modellen aufzurufen. Mit der Modellauswahl können Sie außerdem festlegen, welche Modelle in den einzelnen Diagrammen angezeigt werden. Bestenliste anzeigen