Comparación de modelos de IA pequeños con pesos abiertos (4B-40B)

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

Modelos de IA con pesos abiertos de entre 4B y 40B parámetros.

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.

Qwen3.8 27B (xhigh) y

Qwen3.8 27B (medium) son los modelos pequeños con pesos abiertos, definidos como aquellos con 4B-40B parámetros de mayor inteligencia, seguidos por

Qwen3.8 27B (low) y

Qwen3.6 27B.

Aspectos destacados

Openness

Artificial Analysis Openness Index · Higher is better

Updated

Inteligencia

Artificial Analysis Intelligence Index · Higher is better

Parámetros totales

Parámetros entrenables en miles de millones

Openness

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)

Inteligencia

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.2 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Estimate (independent evaluation forthcoming)

Artificial Analysis Intelligence Index v4.2 includes: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, 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.

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

AA-Briefcase

Agentic knowledge work, (Elo-500)/2000

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

GDP.pdfNew

Professional document reasoning, All-pass

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR v1.1

Long context reasoning

AutomationBench-AA

Agentic SaaS workflows

No data available

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AA

Agentic business operations

GPQA Diamond

Scientific reasoning

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

No data available

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

No data available

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

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

Tamaño

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference

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

Intelligence Index vs. Total Parameters

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

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
Qwen3.8 27B (xhigh)	Alibaba	41	27B	256k	$0.4	44	🤗	+4	Ver
Qwen3.8 27B (medium)	Alibaba	35	27B	256k	$0.4	53	🤗		Ver
Qwen3.8 27B (low)	Alibaba	34	27B	256k	$0.4	53	🤗		Ver
Qwen3.6 27B (Reasoning)	Alibaba	29	27.8B	262k	$0.9	56	🤗	+2	Ver
Qwen3.8 27B (Non-reasoning)	Alibaba	26	27B	256k	$0.4	51	🤗		Ver
Qwen3.6 35B A3B (Reasoning)	Alibaba	26	36B 3B activos en inferencia	262k	$0.6	129	🤗	+5	Ver
G9v3-39A5B	AI9Stars	26	39B 5B activos en inferencia	131k	-	-	🤗		Ver
Muse Glimmer (high)	Meta	24	30B	131k	$0.2	100	🤗		Ver
Qwen3.6 27B (Non-reasoning)	Alibaba	23	27.8B	262k	$0.9	56	🤗	+2	Ver
Gemma 4 31B (Reasoning)	Google	22	30.7B	256k	-	35	🤗	+12	Ver
Gemma 4 26B A4B (Reasoning)	Google	19	25.2B 3.8B activos en inferencia	256k	$0.1	-	🤗	+5	Ver
Qwen3.6 35B A3B (Non-reasoning)	Alibaba	17	36B 3B activos en inferencia	262k	$0.6	137	🤗	+4	Ver

Comparación de modelos de IA pequeños con pesos abiertos (4B-40B)

Openness

Inteligencia

Parámetros totales

Openness

Artificial Analysis Openness Index: Score

Inteligencia

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Tamaño

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

Ventana de contexto

Context Window

Context Window for RAG

Context Window

Más detalles