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.

Nemotron 3.5 Super VL und

Ling-3.0-flash-VL weisen unter den mittelgroßen Modellen mit offenen Gewichten, definiert als Modelle mit 40B-150B Parametern die höchste Intelligenz auf, gefolgt von

Ling-3.0-flash-Fin und

Nemotron 3.5 Bolt 74B-A9B.

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: Wert

Der Openness Index bewertet die Offenheit von Modellen auf einer normierten Skala von 0 bis 100 (höher bedeutet offener)

Intelligenz

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Estimate (independent evaluation forthcoming)

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Evaluations

Evaluations measured independently by Artificial Analysis · AA-PersonalityBench scores are percentile ranks from 1 to 100

AA-Briefcase v1.1

Agentic knowledge work, Elo

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AutomationBench-AA

Agentic SaaS workflows

GDPval-AA v2.1

Agentic real-world work tasks, Elo

Humanity's Last Exam

Reasoning & knowledge

GDP.pdf

Professional document reasoning, All-pass

Terminal-Bench 4.0

Agentic coding & terminal use

AA-LCR v1.1

Long context reasoning

SciCodeUnder review

Coding

CritPt

Physics reasoning

Terminal-Bench-Science 0.1New

Agentic scientific research workflows in a terminal

FrontierCode 1.1New

Agentic software engineering in open-source repositories

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

Harvey LAB-AA v1.1Updated

Legal agentic work, Hallucination-Gated All-Pass Rate

No data available

EnterpriseOps-Gym-AA

Agentic business operations

AA-3DNew

Agentic interactive 3D experiences, Elo

No data available

ITBench-AA

Kubernetes incident root-cause analysis

MLCR-AAUpdated

Medical long context reasoning

MMMU-Pro

Visual reasoning

AA-PersonalityBench: Expressiveness ScoreNew

Rich, varied, well-crafted language

AA-PersonalityBench: Organization ScoreNew

Well-structured, scannable, answer-first

AA-PersonalityBench: Transparency ScoreNew

Truthful, acknowledges uncertainty, non-sycophantic

AA-PersonalityBench: Slop ScoreNew

Use of filler and generic language

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

Größe

Modellgröße: Gesamtparameter und aktive Parameter

Comparison between total model parameters and parameters active during inference (billions)

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 im Vergleich zu aktiven Parametern

Artificial Analysis Intelligence Index · Active parameters at inference time (billions)

Most attractive quadrant

Pareto line

Intelligence Index vs. Gesamtparameter

Artificial Analysis Intelligence Index · Size in parameters (billions)

Most attractive quadrant

Pareto line

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: tokens limit · Higher is better

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
Nemotron 3.5 Super VL	NVIDIA	26	120B 12B während der Inferenz aktiv	1M	$0.1	453	🤗	+5	Anzeigen
Ling-3.0-flash-VL	InclusionAI	25	124B 5.5B während der Inferenz aktiv	262k	-	-	🤗	-	Anzeigen
Ling-3.0-flash-Fin	InclusionAI	23	124B 5.1B während der Inferenz aktiv	262k	-	-	🤗	-	Anzeigen
Nemotron 3.5 Bolt 74B-A9B	NVIDIA	21	74B 9B während der Inferenz aktiv	262k	-	-	🤗	-	Anzeigen
Qwen3.5 122B A10B (Non-reasoning)	Alibaba	18	125B 10B während der Inferenz aktiv	262k	$0.7	142	🤗		Anzeigen
Qwen3.5 122B A10B (Reasoning)	Alibaba	16	125B 10B während der Inferenz aktiv	262k	$0.7	131	🤗		Anzeigen
Mistral Medium 3.5	Mistral	14	128B	256k	$1.2	159	🤗		Anzeigen
HyperNova 60B 2605 (High, Based on gpt-oss-120b)	Multiverse Computing	12	58.7B 4.8B während der Inferenz aktiv	131k	-	-	🤗	-	Anzeigen
gpt-oss-120b (High)	OpenAI	12	117B 5.1B während der Inferenz aktiv	131k	$0.2	208	🤗	+14	Anzeigen
K2 Think V2	Institute of Foundation Models	11	70B	262k	-	-	🤗	-	Anzeigen
LongCat Flash Lite	LongCat	11	68.5B 3B während der Inferenz aktiv	256k	-	-	🤗	-	Anzeigen
Mistral Small 4 (Reasoning)	Mistral	11	119B 6.5B während der Inferenz aktiv	256k	$0.1	183	🤗		Anzeigen

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

Offenheit

Intelligenz

Parameter insgesamt

Offenheit

Artificial Analysis Openness Index: Wert

Intelligenz

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Größe

Modellgröße: Gesamtparameter und aktive Parameter

Total Parameters

Active Parameters at Inference Time

Intelligence Index im Vergleich zu aktiven Parametern

Artificial Analysis Intelligence Index

Active Parameters at Inference Time

Intelligence Index vs. Gesamtparameter

Artificial Analysis Intelligence Index

Total Parameters

Kontextfenster

Kontextfenster

Context Window for RAG

Context Window

Weitere Details