Comparisons of Small Open Source AI Models (4B-40B)

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

Open source AI models with between 4B to 40B parameters.

Models are considered open source (also commonly referred to as open weights) where their weights are accessible to download. This allows self-hosting on your own infrastructure and enables customizing the model such as through fine-tuning.

For more details including relating to our methodology, see our FAQs.

Qwen3.8 27B (xhigh) and

Qwen3.8 27B (medium) are the highest intelligence Small open source models, defined as those with 4B-40B parameters, followed by

Qwen3.8 27B (low) &

K2 Horizon MoVA 36B A4B.

Highlights

Openness

Artificial Analysis Openness Index · Higher is better

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Total Parameters

Trainable parameters in billions

Openness

Artificial Analysis Openness Index: Score

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

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, 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 includes: AA-Briefcase, GDPval-AA v2, 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.

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 4.0New

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

𝜏³-Banking

Agentic tool use

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

MLCR-AANew

Medical long context reasoning

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

Size

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.

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).

Further details

							Weights		Provider Benchmarks
Qwen3.8 27B (xhigh)	Alibaba	34	27B	256k	$0.4	44	🤗	+5	View
Qwen3.8 27B (medium)	Alibaba	28	27B	256k	$0.4	50	🤗		View
Qwen3.8 27B (low)	Alibaba	26	27B	256k	$0.4	51	🤗		View
K2 Horizon MoVA 36B A4B	MBZUAI Institute of Foundation Models	26	36B 4B active at inference time	524k	-	-	🤗	-	View
Qwen3.8 27B (Non-reasoning)	Alibaba	22	27B	256k	$0.4	50	🤗		View
G9v3-39A5B	AI9Stars	22	39B 5B active at inference time	131k	-	-	🤗		View
K2 Horizon 7B	MBZUAI Institute of Foundation Models	21	7B	524k	-	-	🤗	-	View
Qwen3.6 35B A3B (Reasoning)	Alibaba	19	36B 3B active at inference time	262k	$0.6	127	🤗	+5	View
Muse Glimmer (high)	Meta	18	30B	131k	$0.2	99	🤗		View
Gemma 4 26B A4B (Reasoning)	Google	17	25.2B 3.8B active at inference time	256k	$0.1	-	🤗	+5	View
Gemma 4 31B (Reasoning)	Google	15	30.7B	256k	-	35	🤗	+12	View
Qwen3.6 35B A3B (Non-reasoning)	Alibaba	15	36B 3B active at inference time	262k	$0.6	131	🤗	+4	View

Comparisons of Small Open Source AI Models (4B-40B)

Openness

Intelligence

Total Parameters

Openness

Artificial Analysis Openness Index: Score

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Size

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

Context Window

Context Window

Context Window for RAG

Context Window

Further details