Comparison of Open Source Models

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

Comparison and analysis of open source AI models across key performance metrics including quality, performance, inference speed, context window, parameter count & licensing details.

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 relating to our methodology, see our FAQs.

DeepSeek V4.1 Flash 1017 (max) and

GLM-5.3 (max) are the highest intelligence open source models, followed by

MiMo-V2.6-Pro &

Ling 3.1 Flash 1019.

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)

Open Source Progress

Open Weights vs. Proprietary: Artificial Analysis Progress Index v1, Over Time

Item response theory estimate of general capability across Artificial Analysis evaluations · Highest-scoring effort variant shown

We calculate the Artificial Analysis Progress Index v1 using item response theory, which estimates model capability and task difficulty together from our benchmark results. This lets us compare models tested on different benchmarks over time.

We estimate task difficulty from which models succeed or fail, while estimating each model's capability from its results across tasks.

For example, an older model might have been tested on easier benchmarks and a newer model on harder ones. Models tested on both sets help us estimate the difference in difficulty and compare the older and newer models on the same scale.

Each line shows the highest-scoring model available at that point in time within its license category, using each model’s highest-scoring effort variant. Read the Progress Index v1 methodology.

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.

Open Source: Artificial Analysis Progress Index v1 by Lab, Over Time

Item response theory estimate of general capability across Artificial Analysis evaluations · Highest-scoring effort variant shown

We estimate task difficulty from which models succeed or fail, while estimating each model's capability from its results across tasks.

Each lab’s line shows its highest-scoring open weights model available at that point in time, using each model’s highest-scoring effort variant. Read the Progress Index v1 methodology.

Open Source: Artificial Analysis Progress Index v1 by Size, Over Time

Item response theory estimate of general capability across Artificial Analysis evaluations · Highest-scoring effort variant shown

We estimate task difficulty from which models succeed or fail, while estimating each model's capability from its results across tasks.

Each line shows the highest-scoring open weights model available at that point in time within its size category, using each model’s highest-scoring effort variant. Read the Progress Index v1 methodology.

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.

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Artificial Analysis Intelligence Index v5.0 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1. 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 v1.1 AccuracyUpdated

Knowledge

AA-Omniscience v1.1 Non-Hallucination RateUpdated

1 - hallucination rate

AutomationBench-AA

Agentic SaaS workflows

Terminal-Bench-Science 0.1New

Agentic scientific research workflows in a terminal

FrontierCode 2.0New

Agentic software engineering in open-source repositories

HLE-DiamondNew

Reasoning & knowledge

GDP.pdf

Professional document reasoning, All-pass

Terminal-Bench 4.0

Agentic coding & terminal use

CritPt v2 (Hard Subset)

Physics reasoning

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

GDPval-AA v2.1

Agentic real-world work tasks, Elo

AA-3DNew

Agentic interactive 3D experiences, Elo

Code2Video-AANew

Product and brand videos designed in code, Elo

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.

Size

Intelligence Index By Model Size

Model Size: Total and Active Parameters

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. Active Parameters

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

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
DeepSeek V4.1 Flash 1017 (Max)	DeepSeek	32	552B 16B active at inference time	1M	$0.2	184	🤗	+21	View
GLM-5.3 (Max)	Z AI	32	753B 40B active at inference time	1M	$0.9	86	🤗	+24	View
MiMo-V2.6-Pro	Xiaomi	30	1.0T 42B active at inference time	1M	$0.2	66	🤗		View
Ling 3.1 Flash 1019	InclusionAI	29	560B 25B active at inference time	1M	$0.2	-	🤗		View
Step 5 Preview	StepFun	29	600B 27B active at inference time	1M	$0.5	181	🤗		View
Muse Spark Open (Xhigh)	Meta	25	816B 42B active at inference time	1M	$0.8	153	🤗	+3	View
Qwen3.8 27B (Xhigh)	Alibaba	20	27B	256k	$0.5	40	🤗	+9	View
K2 Horizon 375B A23B	Institute of Foundation Models	18	375B 23B active at inference time	524k	$0	934	🤗		View
Beam 1.0	Reflection	18	501B 23B active at inference time	1M	$0.2	345	🤗	+2	View
Nemotron 3.5 Super VL	NVIDIA	14	120B 12B active at inference time	1M	$0.1	447	🤗	+5	View
Inkling (Xhigh)	Thinking Machines	12	975B 41B active at inference time	1M	$0.7	218	🤗	+4	View

Comparison of Open Source Models

Openness

Intelligence

Total Parameters

Openness

Artificial Analysis Openness Index: Score

Open Source Progress

Open Weights vs. Proprietary: Artificial Analysis Progress Index v1, Over Time

How the Progress Index v1 is calculated

Open Weights

Open Source: Artificial Analysis Progress Index v1 by Lab, Over Time

How the Progress Index v1 is calculated

Open Source: Artificial Analysis Progress Index v1 by Size, Over Time

How the Progress Index v1 is calculated

Model Size Classifications

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Size

Intelligence Index By Model Size

Artificial Analysis Intelligence Index

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