Comparisons of Large Open Source AI Models (>150B)

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

Open source AI models with over 150B 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. Click on any model to see detailed metrics. For more details including relating to our methodology, see our FAQs.

Kimi K2.6 and

MiMo-V2.5-Pro are the highest intelligence Large open source models, defined as those with >150B parameters, followed by

DeepSeek V4 Pro (Max) &

GLM-5.1.

Highlights

Openness

Artificial Analysis Openness Index · Higher is better

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Total Parameters

Trainable parameters in billions

Openness

Artificial Analysis Openness Index: Results

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

Reasoning models are indicated by a lightbulb icon

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.0 incorporates 10 evaluations: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt

Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. 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

GDPval-AA

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

Terminal-Bench Hard

Agentic coding & terminal use

𝜏²-Bench Telecom

Agentic tool use

AA-LCR

Long context reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

SciCode

Coding

IFBench

Instruction following

CritPt

Physics reasoning

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon.

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

Reasoning models are indicated by a lightbulb icon

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 vs. Active Parameters

Active parameters at inference time · Artificial Analysis Intelligence Index

Most attractive quadrant

Alibaba

DeepSeek

Kimi

MiniMax

NVIDIA

StepFun

Tencent

Xiaomi

Z AI

Reasoning models are indicated by a lightbulb icon.

Intelligence vs. Total Parameters

Artificial Analysis Intelligence Index · Size in parameters (billions)

Most attractive quadrant

Alibaba

DeepSeek

Kimi

MiniMax

NVIDIA

StepFun

Tencent

Xiaomi

Z AI

Reasoning models are indicated by a lightbulb icon.

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

Reasoning models are indicated by a lightbulb icon

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
Kimi K2.6	Kimi	54	1.0KB 32B active at inference time	256k	$0.7	46	🤗	+12	View
MiMo-V2.5-Pro	Xiaomi	54	1.0KB 42B active at inference time	1.00M	$0.2	43	🤗		View
DeepSeek V4 Pro (Reasoning, Max Effort)	DeepSeek	52	1.6KB 49B active at inference time	1.00M	$0.2	62	🤗	+8	View
GLM-5.1 (Reasoning)	Z AI	51	744B 40B active at inference time	200k	$0.9	78	🤗	+9	View
DeepSeek V4 Pro (Reasoning, High Effort)	DeepSeek	50	1.6KB 49B active at inference time	1.00M	$0.2	61	🤗	+8	View
MiniMax-M2.7	MiniMax	50	230B 10B active at inference time	205k	$0.2	111	🤗	+3	View
MiMo-V2.5	Xiaomi	49	310B 15B active at inference time	1.00M	$0.1	76	🤗	+2	View
Nemotron 3 Ultra 550B A55B (Reasoning)	NVIDIA	48	550B 55B active at inference time	262k	$0.5	159	Not available	+4	View
DeepSeek V4 Flash (Reasoning, Max Effort)	DeepSeek	47	284B 13B active at inference time	1.00M	$0.1	116	🤗	+4	View
DeepSeek V4 Flash (Reasoning, High Effort)	DeepSeek	46	284B 13B active at inference time	1.00M	$0.1	-	🤗	+4	View
Qwen3.5 397B A17B (Reasoning)	Alibaba	45	397B 17B active at inference time	262k	$0.9	52	🤗	+9	View
GLM-5.1 (Non-reasoning)	Z AI	44	744B 40B active at inference time	200k	$0.9	82	🤗	+5	View
Kimi K2.6 (Non-reasoning)	Kimi	43	1.0KB 32B active at inference time	256k	$0.7	44	🤗	+9	View
Step 3.7 Flash	StepFun	43	198B 11B active at inference time	256k	$0.2	116	🤗		View
Hy3-preview (Reasoning)	Tencent	42	295B 21B active at inference time	256k	$0.1	99	🤗		View
MiMo-V2-Flash (Feb 2026)	Xiaomi	41	309B 15B active at inference time	256k	$0.1	143	🤗		View
Qwen3.5 397B A17B (Non-reasoning)	Alibaba	40	397B 17B active at inference time	262k	$0.9	53	🤗	+6	View
DeepSeek V4 Pro (Non-reasoning)	DeepSeek	39	1.6KB 49B active at inference time	1.00M	$0.2	61	🤗	+2	View
Ring-2.6-1T	InclusionAI	38	1.0KB 63B active at inference time	262k	$0.5	128	🤗		View
Command A+	Cohere	37	218B 25B active at inference time	192k	-	202	🤗		View
DeepSeek V4 Flash (Non-reasoning)	DeepSeek	36	284B 13B active at inference time	1.00M	$0.1	113	🤗		View
MiMo-V2.5-Pro (Non-reasoning)	Xiaomi	36	1.0KB 41.7B active at inference time	1.00M	$0.6	55	🤗		View
Hy3-preview (Non-reasoning)	Tencent	34	295B 21B active at inference time	256k	$0.1	95	🤗		View
Ling-2.6-1T	InclusionAI	34	1.0KB 63B active at inference time	262k	$0.5	-	🤗		View
K-EXAONE (Reasoning)	LG AI Research	32	236B 23B active at inference time	256k	-	-	🤗	-	View
Trinity Large Thinking	Arcee AI	32	399B 13B active at inference time	512k	$0.2	198	🤗		View
MiMo-V2-Flash (Non-reasoning)	Xiaomi	30	309B 15B active at inference time	256k	$0.1	142	🤗		View
K-EXAONE (Non-reasoning)	LG AI Research	23	236B 23B active at inference time	256k	-	-	🤗	-	View
Mistral Large 3	Mistral	23	675B 41B active at inference time	256k	$0.6	52	🤗		View
Hermes 4 - Llama-3.1 405B (Reasoning)	Nous Research	19	406B	128k	$1.2	40	🤗		View
Llama 4 Maverick	Meta	18	402B 17B active at inference time	1.00M	$0.3	111	🤗	+6	View
Hermes 4 - Llama-3.1 405B (Non-reasoning)	Nous Research	18	406B	128k	$1.2	40	🤗		View
Llama 3.1 Instruct 405B	Meta	17	405B	128k	$3.1	61	🤗		View
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)	NVIDIA	15	253B	128k	$0.7	52	🤗		View
ERNIE 4.5 300B A47B	Baidu	15	300B 47B active at inference time	131k	$0.4	-	🤗		View
R1 1776	Perplexity	12	671B 37B active at inference time	128k	-	-	🤗	-	View
Jamba 1.7 Large	AI21 Labs	11	398B 94B active at inference time	256k	$2.6	60	🤗		View
Cogito v2.1 (Reasoning)	Deep Cogito	-	671B 37B active at inference time	128k	$1.3	69	🤗		View

Comparisons of Large Open Source AI Models (>150B)

Openness

Intelligence

Total Parameters

Openness

Artificial Analysis Openness Index: Results

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 vs. Active Parameters

Artificial Analysis Intelligence Index

Active Parameters at Inference Time

Intelligence vs. Total Parameters

Artificial Analysis Intelligence Index

Total Parameters

Context Window

Context Window

Context Window for RAG

Context Window

Further details