Comparação de modelos pequenos de IA de pesos abertos (4B-40B)

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

Modelos de IA de pesos abertos com 4B a 40B parâmetros.

Os modelos são considerados de pesos abertos (também chamados frequentemente de código aberto) quando seus pesos estão disponíveis para download. Isso permite a auto-hospedagem em sua própria infraestrutura e a personalização do modelo, por exemplo, por meio de ajuste fino.

Para mais detalhes sobre nossa metodologia, consulte as perguntas frequentes.

Qwen3.8 27B (xhigh) e

Qwen3.8 27B (medium) são os modelos com maior inteligência entre os modelos pequenos de pesos abertos, definidos como aqueles com 4B-40B parâmetros, seguidos por

Qwen3.8 27B (low) e

K2 Horizon MoVA 36B A4B.

Destaques

Abertura

Artificial Analysis Openness Index · Higher is better

Updated

Inteligência

Artificial Analysis Intelligence Index · Higher is better

Parâmetros totais

Parâmetros treináveis em bilhões

Abertura

Artificial Analysis Openness Index: Score

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

Inteligência

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Estimate (independent evaluation forthcoming)

Artificial Analysis Intelligence Index v4.3 includes: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, 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.

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

AutomationBench-AAUpdated

Agentic SaaS workflows

Terminal-Bench v4.0New

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

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AA

Agentic business operations

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

No data available

IFBench

Instruction following

𝜏³-Banking

Agentic tool use

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.

Tamanho

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.

Janela 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).

Mais detalhes

							Pesos		Benchmarks de provedores
Qwen3.8 27B (xhigh)	Alibaba	34	27B	256k	$0.4	46	🤗	+5	Ver
Qwen3.8 27B (medium)	Alibaba	28	27B	256k	$0.4	52	🤗		Ver
Qwen3.8 27B (low)	Alibaba	26	27B	256k	$0.4	51	🤗		Ver
K2 Horizon MoVA 36B A4B	MBZUAI Institute of Foundation Models	26	36B 4B ativos durante a inferência	524k	-	-	🤗	-	Ver
Qwen3.8 27B (Non-reasoning)	Alibaba	22	27B	256k	$0.4	51	🤗		Ver
Qwen3.6 27B (Reasoning)	Alibaba	22	27.8B	262k	$0.9	57	🤗	+2	Ver
G9v3-39A5B	AI9Stars	22	39B 5B ativos durante a inferência	131k	-	-	🤗		Ver
K2 Horizon 7B	MBZUAI Institute of Foundation Models	21	7B	524k	-	-	🤗	-	Ver
Qwen3.6 27B (Non-reasoning)	Alibaba	20	27.8B	262k	$0.9	58	🤗	+2	Ver
Qwen3.6 35B A3B (Reasoning)	Alibaba	19	36B 3B ativos durante a inferência	262k	$0.6	127	🤗	+5	Ver
Muse Glimmer (high)	Meta	18	30B	131k	$0.2	90	🤗		Ver
Gemma 4 26B A4B (Reasoning)	Google	17	25.2B 3.8B ativos durante a inferência	256k	$0.1	-	🤗	+5	Ver

Comparação de modelos pequenos de IA de pesos abertos (4B-40B)

Abertura

Inteligência

Parâmetros totais

Abertura

Artificial Analysis Openness Index: Score

Inteligência

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Tamanho

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

Janela de contexto

Context Window

Context Window for RAG

Context Window

Mais detalhes