Comparación de modelos con pesos abiertos

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

Comparación y análisis de modelos de IA con pesos abiertos en métricas clave como calidad, rendimiento, velocidad de inferencia, ventana de contexto, número de parámetros y detalles de licencia.

Consideramos que un modelo tiene pesos abiertos (también denominado comúnmente «open source») cuando sus pesos están disponibles para descargar. Esto permite alojarlo en infraestructura propia y personalizarlo, por ejemplo, mediante ajuste fino.

Para más detalles sobre nuestra metodología, consulta nuestras FAQs.

MiMo-V2.6-Pro y

GLM-5.3 (max) son los modelos con pesos abiertos de mayor inteligencia, seguidos por

Step 5 Preview y

Kimi K3 (max).

Openness

Artificial Analysis Openness Index · Higher is better

Inteligencia

Artificial Analysis Intelligence Index · Higher is better

Parámetros totales

Parámetros entrenables en miles de millones

Openness

Artificial Analysis Openness Index: puntuación

El Openness Index mide la apertura de los modelos en una escala normalizada de 0 a 100 (cuanto más alta, mayor apertura)

Progreso de los modelos con pesos abiertos

Progreso de la inteligencia de modelos de pesos abiertos vs. propietarios

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

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.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

Evolución de la inteligencia de los modelos de lenguaje con pesos abiertos por laboratorio

Evolución de la inteligencia de los modelos con pesos abiertos por tamaño

Tiny: Less than or equal to 4B parameters. These are usually the smallest models in terms of resource demand.
Small: Less than 40B parameters.
Medium: Between 40B-150B parameters.
Large: Over 150B parameters.

Inteligencia

Artificial Analysis Intelligence Index

Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

AA-Briefcase v1.1Updated

Agentic knowledge work, (Elo-500)/2000

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AutomationBench-AA

Agentic SaaS workflows

GDPval-AA v2.1Updated

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

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

CritPtUnder review

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

EnterpriseOps-Gym-AA

Agentic business operations

ITBench-AA

Kubernetes incident root-cause analysis

MLCR-AA

Medical long context reasoning

MMMU-Pro

Visual reasoning

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

Tamaño

Intelligence Index por tamaño de modelo

Tamaño del modelo: parámetros totales y activos

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 vs. parámetros activos

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

Most attractive quadrant

Pareto line

Intelligence Index vs. parámetros totales

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.

Ventana de contexto

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).

Más detalles

							Pesos		Benchmarks de proveedores
MiMo-V2.6-Pro	Xiaomi	46	1.0T 42B activos en inferencia	1M	$0.2	48	🤗	+2	Ver
GLM-5.3 (Max)	Z AI	45	753B 40B activos en inferencia	1M	$0.9	74	🤗	+24	Ver
Step 5 Preview	StepFun	44	600B 27B activos en inferencia	1M	$0.5	90	🤗		Ver
Kimi K3 (Max)	Kimi	44	2.8T 104B activos en inferencia	1M	$2.3	43	🤗	+17	Ver
GLM-5.3-Flash	Z AI	42	320B 18B activos en inferencia	1M	$0.1	66	🤗	+23	Ver
DeepSeek V4.1 Flash (Max)	DeepSeek	39	552B 16B activos en inferencia	1M	$0.2	178	🤗	+23	Ver
Muse Spark Open (Xhigh)	Meta	39	816B 42B activos en inferencia	1M	$0.8	111	🤗		Ver
Qwen3.8 27B (Xhigh)	Alibaba	34	27B	256k	$0.5	41	🤗	+9	Ver
K2 Horizon 375B A23B	Institute of Foundation Models	31	375B 23B activos en inferencia	524k	-	-	🤗	-	Ver
Beam 1.0	Reflection	30	501B 23B activos en inferencia	1M	-	-	🤗	-	Ver
MiniMax-M3	MiniMax	29	428B 23B activos en inferencia	1M	$0.2	95	🤗	+11	Ver
Nemotron 3.5 Super VL	NVIDIA	26	120B 12B activos en inferencia	1M	$0.1	251	🤗	+3	Ver
Inkling (Xhigh)	Thinking Machines	25	975B 41B activos en inferencia	1M	$0.7	192	🤗	+4	Ver

Comparación de modelos con pesos abiertos

Openness

Inteligencia

Parámetros totales

Openness

Artificial Analysis Openness Index: puntuación

Progreso de los modelos con pesos abiertos

Progreso de la inteligencia de modelos de pesos abiertos vs. propietarios

Artificial Analysis Intelligence Index

Open Weights

Evolución de la inteligencia de los modelos de lenguaje con pesos abiertos por laboratorio

Artificial Analysis Intelligence Index

Evolución de la inteligencia de los modelos con pesos abiertos por tamaño

Artificial Analysis Intelligence Index

Model Size Classifications

Inteligencia

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Tamaño

Intelligence Index por tamaño de modelo

Artificial Analysis Intelligence Index

Tamaño del modelo: parámetros totales y activos

Total Parameters

Active Parameters at Inference Time

Intelligence Index vs. parámetros activos

Artificial Analysis Intelligence Index

Active Parameters at Inference Time

Intelligence Index vs. parámetros totales

Artificial Analysis Intelligence Index

Total Parameters

Ventana de contexto

Ventana de contexto

Context Window for RAG

Context Window

Más detalles