Vergleich mittelgroßer KI-Modelle mit offenen Gewichten (40B-150B)

Name: Offenheit
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

KI-Modelle mit offenen Gewichten und 40B bis 150B Parametern.

Modelle gelten als Modelle mit offenen Gewichten (häufig auch als Open Source bezeichnet), wenn ihre Gewichte zum Download verfügbar sind. Dadurch können sie auf der eigenen Infrastruktur gehostet und beispielsweise durch Fine-Tuning angepasst werden.

Weitere Details, auch zu unserer Methodik, finden Sie in unseren FAQs.

Qwen3.5 122B A10B und

Mistral Medium 3.5 weisen unter den mittelgroßen Modellen mit offenen Gewichten, definiert als Modelle mit 40B-150B Parametern die höchste Intelligenz auf, gefolgt von

Qwen3.5 122B A10B und

NVIDIA Nemotron 3 Super.

Wichtigste Ergebnisse

Offenheit

Artificial Analysis Openness Index · Higher is better

Intelligenz

Artificial Analysis Intelligence Index · Higher is better

Parameter insgesamt

Trainierbare Parameter in Milliarden

Offenheit

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

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

Estimate (independent evaluation forthcoming)

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.

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.

Größe

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.

Intelligence Index vs. Active Parameters

Artificial Analysis Intelligence Index · Active parameters at inference time

Most attractive quadrant

Pareto line

Reasoning models are indicated by a lightbulb icon

Intelligence Index vs. Total Parameters

Artificial Analysis Intelligence Index · Size in parameters (billions)

Most attractive quadrant

Pareto line

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.

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).

Weitere Details

							Gewichte		Anbieter-Benchmarks
Qwen3.5 122B A10B (Reasoning)	Alibaba	32	125B 10B während der Inferenz aktiv	262k	$0.7	125	🤗	+2	Anzeigen
Mistral Medium 3.5	Mistral	30	128B	256k	$1.2	134	🤗		Anzeigen
Qwen3.5 122B A10B (Non-reasoning)	Alibaba	28	125B 10B während der Inferenz aktiv	262k	$0.7	140	🤗		Anzeigen
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)	NVIDIA	25	120.6B 12.7B während der Inferenz aktiv	1M	$0.3	143	🤗		Anzeigen
gpt-oss-120b (high)	OpenAI	24	117B 5.1B während der Inferenz aktiv	131k	$0.2	185	🤗	+18	Anzeigen
Qwen3 Coder Next	Alibaba	21	79.7B 3B während der Inferenz aktiv	256k	$0.4	133	🤗		Anzeigen
Mistral Small 4 (Reasoning)	Mistral	20	119B 6.5B während der Inferenz aktiv	256k	$0.2	158	🤗		Anzeigen
Devstral 2	Mistral	19	125B	256k	-	43	🤗		Anzeigen
HyperNova 60B 2605	Multiverse Computing	18	58.7B 4.8B während der Inferenz aktiv	131k	$0.1	349	🤗		Anzeigen
K2 Think V2	MBZUAI Institute of Foundation Models	17	70B	262k	-	-	🤗	-	Anzeigen
LongCat Flash Lite	LongCat	17	68.5B 3B während der Inferenz aktiv	256k	-	-	🤗	-	Anzeigen
Qwen3 Next 80B A3B (Reasoning)	Alibaba	17	80B 3B während der Inferenz aktiv	262k	$1.1	205	🤗	+2	Anzeigen

Vergleich mittelgroßer KI-Modelle mit offenen Gewichten (40B-150B)

Offenheit

Intelligenz

Parameter insgesamt

Offenheit

Artificial Analysis Openness Index: Score

Intelligenz

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Größe

Model Size: Total and Active Parameters

Total Parameters

Active Parameters at Inference Time

Intelligence Index vs. Active Parameters

Artificial Analysis Intelligence Index

Active Parameters at Inference Time

Intelligence Index vs. Total Parameters

Artificial Analysis Intelligence Index

Total Parameters

Kontextfenster

Context Window

Context Window for RAG

Context Window

Weitere Details