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. Click on any model to see detailed metrics. For more details relating to our methodology, see our FAQs.

GLM-5.2 (max) and

MiniMax-M3 are the highest intelligence open source models, followed by

DeepSeek V4 Pro (Max) &

Kimi K2.6.

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)

Reasoning models are indicated by a lightbulb icon

Open Source Progress

Progress in Open Weights vs. Proprietary Intelligence

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Reasoning models are indicated by a lightbulb icon.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).

Open Source Language Models Intelligence By Lab Over Time

Reasoning models are indicated by a lightbulb icon.

Open Source Models Intelligence By Size Over Time

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Reasoning models are indicated by a lightbulb icon.

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.

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Estimate (independent evaluation forthcoming)

Reasoning models are indicated by a lightbulb icon

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

GDPval-AA v2Updated

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

𝜏³-BankingNew

Agentic tool use

Terminal-Bench v2.1New

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

IFBench

Instruction following

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

Intelligence Index By Model Size

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Estimate (independent evaluation forthcoming)

Large Models (>150B)

Medium Models (40B-150B)

Small Models (4B-40B)

Reasoning models are indicated by a lightbulb icon.

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.

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

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

Google

Kimi

MBZUAI Institute of Foundation Models

MiniMax

Mistral

NVIDIA

OpenAI

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
GLM-5.2 (max)	Z AI	51	753B 40B active at inference time	1.00M	$0.9	96	🤗	+7	View
MiniMax-M3	MiniMax	44	428B 23B active at inference time	1.00M	$0.2	60	🤗	+4	View
DeepSeek V4 Pro (Reasoning, Max Effort)	DeepSeek	44	1.6KB 49B active at inference time	1.00M	$0.2	84	🤗	? +8	View
Kimi K2.6	Kimi	43	1.0KB 32B active at inference time	256k	$0.7	44	🤗	+13	View
MiMo-V2.5-Pro	Xiaomi	42	1.0KB 42B active at inference time	1.00M	$0.2	54	🤗		View
Kimi K2.7 Code	Kimi	42	1.0KB 32B active at inference time	256k	$0.7	59	🤗	+6	View
DeepSeek V4 Pro (Reasoning, High Effort)	DeepSeek	41	1.6KB 49B active at inference time	1.00M	$0.2	76	🤗	+8	View
DeepSeek V4 Flash (Reasoning, Max Effort)	DeepSeek	40	284B 13B active at inference time	1.00M	$0.1	109	🤗	+4	View
GLM-5.1 (Reasoning)	Z AI	40	744B 40B active at inference time	200k	$0.9	83	🤗	+9	View
MiMo-V2.5	Xiaomi	40	310B 15B active at inference time	1.00M	$0.1	82	🤗	+2	View
GLM-5 (Reasoning)	Z AI	40	744B 40B active at inference time	200k	$0.7	76	🤗	+9	View
MiniMax-M2.7	MiniMax	38	230B 10B active at inference time	205k	$0.2	46	🤗	+3	View
Kimi K2.5 (Reasoning)	Kimi	38	1.0KB 32B active at inference time	256k	$0.6	55	🤗	+12	View
Nemotron 3 Ultra 550B A55B (Reasoning)	NVIDIA	38	550B 55B active at inference time	262k	$0.6	171	Not available	+5	View
DeepSeek V4 Flash (Reasoning, High Effort)	DeepSeek	37	284B 13B active at inference time	1.00M	$0.1	-	🤗	+5	View
Qwen3.6 27B (Reasoning)	Alibaba	37	27.8B	262k	$0.9	59	🤗	+3	View
GLM-5.1 (Non-reasoning)	Z AI	35	744B 40B active at inference time	200k	$0.9	57	🤗	+5	View
Kimi K2.6 (Non-reasoning)	Kimi	35	1.0KB 32B active at inference time	256k	$0.7	45	🤗	+10	View
GLM-4.7 (Reasoning)	Z AI	34	357B 32B active at inference time	200k	$0.7	115	🤗	+7	View
Qwen3.5 27B (Reasoning)	Alibaba	34	27.8B	262k	$0.5	81	🤗	+3	View
Qwen3.5 397B A17B (Reasoning)	Alibaba	34	397B 17B active at inference time	262k	$0.9	51	🤗	+9	View
MiniMax-M2.5	MiniMax	34	230B 10B active at inference time	205k	$0.3	203	🤗	+13	View
Hy3-preview (Reasoning)	Tencent	34	295B 21B active at inference time	256k	$0.1	117	🤗		View
DeepSeek V3.2 (Reasoning)	DeepSeek	33	685B 37B active at inference time	128k	$0.2	-	🤗	+12	View
MiMo-V2-Flash (Feb 2026)	Xiaomi	33	309B 15B active at inference time	256k	$0.1	89	🤗		View
Kimi K2 Thinking	Kimi	33	1.0KB 32B active at inference time	256k	$0.8	123	🤗	+3	View
GLM-5 (Non-reasoning)	Z AI	32	744B 40B active at inference time	200k	$0.7	66	🤗	+3	View
Qwen3.5 122B A10B (Reasoning)	Alibaba	32	125B 10B active at inference time	262k	$0.7	135	🤗	+2	View
Qwen3.5 397B A17B (Non-reasoning)	Alibaba	32	397B 17B active at inference time	262k	$0.9	52	🤗	+6	View
Qwen3.6 35B A3B (Reasoning)	Alibaba	32	36B 3B active at inference time	262k	$0.4	179	🤗	+6	View
MiniMax-M2.1	MiniMax	31	230B 10B active at inference time	205k	$0.4	223	🤗		View
DeepSeek V4 Pro (Non-reasoning)	DeepSeek	31	1.6KB 49B active at inference time	1.00M	$0.2	79	🤗	+2	View
MiMo-V2-Flash (Reasoning)	Xiaomi	31	309B 15B active at inference time	256k	$0.1	87	🤗		View
Ring-2.6-1T	InclusionAI	31	1.0KB 63B active at inference time	262k	$0.5	133	🤗		View
Mistral Medium 3.5	Mistral	30	128B	256k	$1.2	135	🤗		View
Step 3.7 Flash	StepFun	30	198B 11B active at inference time	256k	$0.2	383	🤗		View
Kimi K2.5 (Non-reasoning)	Kimi	29	1.0KB 32B active at inference time	256k	$0.8	54	🤗	+6	View
Gemma 4 31B (Reasoning)	Google	29	30.7B	256k	-	34	🤗	+8	View
Qwen3.5 27B (Non-reasoning)	Alibaba	29	27.8B	262k	$0.5	90	🤗		View
Command A+	Cohere	29	218B 25B active at inference time	192k	-	199	🤗		View
Qwen3.6 27B (Non-reasoning)	Alibaba	29	27.8B	262k	$0.9	63	🤗	+2	View
Qwen3.5 35B A3B (Reasoning)	Alibaba	29	36B 3B active at inference time	262k	$0.4	158	🤗	+2	View
DeepSeek V4 Flash (Non-reasoning)	DeepSeek	29	284B 13B active at inference time	1.00M	$0.1	113	🤗		View
MiniMax-M2	MiniMax	28	230B 10B active at inference time	205k	$0.4	119	🤗		View
Qwen3.5 122B A10B (Non-reasoning)	Alibaba	28	125B 10B active at inference time	262k	$0.7	156	🤗		View
MiMo-V2.5-Pro (Non-reasoning)	Xiaomi	28	1.0KB 41.7B active at inference time	1.00M	$0.6	56	🤗		View
GLM-4.7 (Non-reasoning)	Z AI	27	357B 32B active at inference time	200k	$0.7	117	🤗	+6	View
DeepSeek V3.1 Terminus (Reasoning)	DeepSeek	26	685B 37B active at inference time	128k	$1.7	-	🤗		View
Hy3-preview (Non-reasoning)	Tencent	26	295B 21B active at inference time	256k	$0.1	133	🤗		View
Ling-2.6-1T	InclusionAI	26	1.0KB 63B active at inference time	262k	$0.5	-	🤗		View
Gemma 4 26B A4B (Reasoning)	Google	26	25.2B 3.8B active at inference time	256k	$0.1	-	🤗	+4	View
Step 3.5 Flash	StepFun	26	196B 11B active at inference time	256k	$0.1	211	🤗		View
DeepSeek V3.2 Exp (Reasoning)	DeepSeek	25	685B 37B active at inference time	128k	$0.2	-	🤗		View
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)	NVIDIA	25	120.6B 12.7B active at inference time	1.00M	$0.3	148	🤗	+2	View
GLM-4.6 (Reasoning)	Z AI	25	357B 32B active at inference time	200k	$0.7	50	🤗		View
Qwen3.5 9B (Reasoning)	Alibaba	25	9.65B	262k	$0.1	63	🤗		View
Gemma 4 31B (Non-reasoning)	Google	25	30.7B	256k	$0.2	38	🤗	+4	View
K-EXAONE (Reasoning)	LG AI Research	25	236B 23B active at inference time	256k	-	-	🤗	-	View
DeepSeek V3.2 (Non-reasoning)	DeepSeek	25	685B 37B active at inference time	128k	$0.5	-	🤗	+12	View
Trinity Large Thinking	Arcee AI	24	399B 13B active at inference time	512k	$0.2	154	🤗		View
Qwen3.6 35B A3B (Non-reasoning)	Alibaba	24	36B 3B active at inference time	262k	$0.6	188	🤗	+5	View
gpt-oss-120b (high)	OpenAI	24	117B 5.1B active at inference time	131k	$0.2	341	🤗	+23	View
Kimi K2 0905	Kimi	24	1.0KB 32B active at inference time	256k	$0.8	27	🤗		View
Qwen3.5 35B A3B (Non-reasoning)	Alibaba	23	36B 3B active at inference time	262k	$0.4	173	🤗		View
MiMo-V2-Flash (Non-reasoning)	Xiaomi	23	309B 15B active at inference time	256k	$0.1	93	🤗		View
GLM-4.6 (Non-reasoning)	Z AI	23	357B 32B active at inference time	200k	$0.8	51	🤗		View
EXAONE 4.5 33B	LG AI Research	23	34.4B	262k	-	-	🤗	-	View
GLM-4.7-Flash (Reasoning)	Z AI	23	31.2B 3B active at inference time	200k	$0.1	88	🤗		View
Qwen3 235B A22B 2507 (Reasoning)	Alibaba	22	235B 22B active at inference time	256k	$0.6	48	🤗	+3	View
DeepSeek V3.2 Speciale	DeepSeek	22	685B 37B active at inference time	128k	-	-	🤗	-	View
HyperNova 60B 2605	Multiverse Computing	22	58.7B 4.8B active at inference time	131k	$0.1	360	🤗		View
Gemma 4 12B (Reasoning)	Google	22	12B	256k	$0.1	126	🤗		View
DeepSeek V3.1 Terminus (Non-reasoning)	DeepSeek	21	685B 37B active at inference time	128k	$0.3	-	🤗		View
DeepSeek V3.2 Exp (Non-reasoning)	DeepSeek	21	685B 37B active at inference time	128k	$0.2	-	🤗		View
Nemotron Cascade 2 30B A3B	NVIDIA	21	31.6B 3B active at inference time	1.00M	-	-	🤗	-	View
Apriel-v1.5-15B-Thinker	ServiceNow	21	15B	128k	-	-	🤗		View
Qwen3 Coder Next	Alibaba	21	79.7B 3B active at inference time	256k	$0.4	63	🤗		View
DeepSeek V3.1 (Non-reasoning)	DeepSeek	21	685B 37B active at inference time	128k	$0.7	-	🤗	+7	View
Mistral Small 4 (Reasoning)	Mistral	21	119B 6.5B active at inference time	256k	$0.2	170	🤗		View
DeepSeek V3.1 (Reasoning)	DeepSeek	21	685B 37B active at inference time	128k	$0.7	-	🤗		View
Qwen3 VL 235B A22B (Reasoning)	Alibaba	21	235B 22B active at inference time	262k	$1.4	56	🤗		View
North Mini Code	Cohere	21	30B 3B active at inference time	256k	-	151	Not available		View
Apriel-v1.6-15B-Thinker	ServiceNow	21	15B	128k	-	-	🤗		View
Qwen3.5 9B (Non-reasoning)	Alibaba	20	9.65B	262k	-	-	🤗	-	View
Gemma 4 26B A4B (Non-reasoning)	Google	20	25.2B 3.8B active at inference time	256k	$0.2	40	🤗	+4	View
Qwen3.5 4B (Reasoning)	Alibaba	20	4.66B	262k	$0.0	30	🤗		View
DeepSeek R1 0528 (May '25)	DeepSeek	20	685B 37B active at inference time	128k	$1.6	-	🤗	+3	View
Qwen3 Next 80B A3B (Reasoning)	Alibaba	20	80B 3B active at inference time	262k	$1.1	174	🤗	+5	View
GLM-4.5 (Reasoning)	Z AI	19	355B 32B active at inference time	128k	$0.8	50	🤗		View
Kimi K2	Kimi	19	1.0KB 32B active at inference time	128k	$0.6	27	🤗		View
Ling 2.6 Flash	InclusionAI	19	107B 7.4B active at inference time	262k	$0.1	-	🤗		View
Seed-OSS-36B-Instruct	ByteDance Seed	18	36.2B	512k	$0.2	34	🤗		View
Qwen3 235B A22B 2507 Instruct	Alibaba	18	235B 22B active at inference time	256k	$0.3	58	🤗	+9	View
Qwen3 Coder 480B A35B Instruct	Alibaba	18	480B 35B active at inference time	262k	$0.5	60	🤗	+6	View
Qwen3 VL 32B (Reasoning)	Alibaba	18	33.4B	256k	$1.5	91	🤗		View
gpt-oss-120b (low)	OpenAI	18	117B 5.1B active at inference time	131k	$0.2	355	🤗	+19	View
MiniMax M1 80k	MiniMax	18	456B 45.9B active at inference time	1.00M	$0.7	-	🤗		View
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)	NVIDIA	18	31.6B 3.6B active at inference time	1.00M	$0.1	86	🤗		View
K2 Think V2	MBZUAI Institute of Foundation Models	17	70B	262k	-	-	🤗	-	View
LongCat Flash Lite	LongCat	17	68.5B 3B active at inference time	256k	-	-	🤗		View
HyperCLOVA X SEED Think (32B)	Naver	17	32B	128k	-	-	🤗	-	View
GLM-4.6V (Reasoning)	Z AI	17	108B 12B active at inference time	128k	$0.4	80	🤗		View
K-EXAONE (Non-reasoning)	LG AI Research	17	236B 23B active at inference time	256k	-	-	🤗	-	View
GLM-4.5-Air	Z AI	17	106B 12B active at inference time	128k	$0.3	79	🤗		View
Mistral Large 3	Mistral	16	675B 41B active at inference time	256k	$0.6	51	🤗		View
Ring-1T	InclusionAI	16	1.0KB 50B active at inference time	128k	-	-	🤗	-	View
Qwen3.5 4B (Non-reasoning)	Alibaba	16	4.66B	262k	$0.0	36	🤗		View
Qwen3 30B A3B 2507 (Reasoning)	Alibaba	16	30.5B 3.3B active at inference time	262k	$0.4	146	🤗		View
DeepSeek V3 0324	DeepSeek	16	671B 37B active at inference time	128k	$1.2	-	🤗	+3	View
INTELLECT-3	Prime Intellect	16	107B 12B active at inference time	131k	-	-	🤗	-	View
GLM-4.7-Flash (Non-reasoning)	Z AI	16	31.2B 3B active at inference time	200k	$0.1	144	🤗		View
Devstral 2	Mistral	15	125B	256k	-	44	🤗		View
Solar Open 100B (Reasoning)	Upstage	15	102B 12B active at inference time	128k	-	-	🤗	-	View
Nemotron 3 Nano Omni 30B A3B Reasoning	NVIDIA	15	30B 3B active at inference time	256k	$0.1	280	🤗		View
gpt-oss-20B (high)	OpenAI	15	21B 3.6B active at inference time	131k	$0.1	216	🤗	+10	View
MiniMax M1 40k	MiniMax	14	456B 45.9B active at inference time	1.00M	-	-	🤗	-	View
gpt-oss-20B (low)	OpenAI	14	21B 3.6B active at inference time	131k	$0.1	224	🤗	+9	View
Qwen3 VL 235B A22B Instruct	Alibaba	14	235B 22B active at inference time	262k	$0.5	50	🤗	+2	View
Llama 4 Maverick	Meta	14	402B 17B active at inference time	1.00M	$0.3	93	🤗	+6	View
K2-V2 (high)	MBZUAI Institute of Foundation Models	14	70B	512k	-	-	🤗	-	View
Qwen3 Next 80B A3B Instruct	Alibaba	14	80B 3B active at inference time	262k	$0.7	178	🤗	+4	View
Tri-21B-think Preview	Trillion Labs	14	21B	32.0k	-	-	🤗	-	View
Qwen3 Coder 30B A3B Instruct	Alibaba	14	30.5B 3.3B active at inference time	262k	$0.3	100	🤗		View
Qwen3 235B A22B (Reasoning)	Alibaba	13	235B 22B active at inference time	32.8k	$1.5	60	🤗		View
QwQ 32B	Alibaba	13	32.8B	131k	$0.7	31	🤗		View
Qwen3 VL 30B A3B (Reasoning)	Alibaba	13	30B 3B active at inference time	256k	$0.3	111	🤗		View
Gemma 4 12B (Non-reasoning)	Google	13	12B	262k	$0.1	134	🤗		View
Devstral Small 2	Mistral	13	24B	256k	-	55	🤗		View
Ling-1T	InclusionAI	13	1.0KB 50B active at inference time	128k	-	-	🤗	-	View
DeepSeek R1 (Jan '25)	DeepSeek	13	685B 37B active at inference time	128k	$2.0	-	🤗	+3	View
Gemma 4 E4B (Reasoning)	Google	12	8B 4.5B active at inference time	128k	-	-	🤗	-	View
K2-V2 (medium)	MBZUAI Institute of Foundation Models	12	70B	512k	-	-	🤗	-	View
Llama Nemotron Super 49B v1.5 (Reasoning)	NVIDIA	12	49B	128k	$0.1	49	🤗		View
Mistral Small 4 (Non-reasoning)	Mistral	12	119B 6.5B active at inference time	256k	$0.2	156	🤗		View
Tri-21B-Think	Trillion Labs	12	21B	32.0k	-	-	🤗	-	View
Llama 3.3 Nemotron Super 49B v1 (Reasoning)	NVIDIA	12	49B	128k	-	-	🤗	-	View
Qwen3 4B 2507 (Reasoning)	Alibaba	12	4.02B	262k	-	-	🤗	-	View
MiniCPM5-1B (Reasoning)	OpenBMB	12	1B	128k	-	-	🤗	-	View
Magistral Small 1.2	Mistral	12	24B	128k	$0.6	107	🤗		View
Sarvam 105B (high)	Sarvam	12	106B 10.3B active at inference time	128k	$0.0	96	🤗		View
Devstral Small (May '25)	Mistral	12	23.6B	256k	-	-	🤗	-	View
MiniCPM5-1B (Non-reasoning)	OpenBMB	12	1B	128k	-	-	🤗	-	View
Qwen3 VL 32B Instruct	Alibaba	11	33.4B	256k	$0.9	67	🤗		View
DeepSeek R1 Distill Qwen 32B	DeepSeek	11	32B	128k	-	-	🤗	-	View
GLM-4.6V (Non-reasoning)	Z AI	11	108B 12B active at inference time	128k	$0.4	84	🤗		View
Qwen3 235B A22B (Non-reasoning)	Alibaba	11	235B 22B active at inference time	32.8k	$0.6	61	🤗		View
Magistral Small 1	Mistral	11	23.6B	40.0k	-	-	🤗	-	View
EXAONE 4.0 32B (Reasoning)	LG AI Research	11	32B	131k	-	-	🤗	-	View
Qwen3 VL 8B (Reasoning)	Alibaba	11	8.77B	256k	$0.4	111	🤗		View
Qwen3 32B (Reasoning)	Alibaba	10	32.8B	32.8k	$0.2	61	🤗	+3	View
DeepSeek V3 (Dec '24)	DeepSeek	10	671B 37B active at inference time	128k	$0.4	-	🤗	+2	View
DeepSeek R1 0528 Qwen3 8B	DeepSeek	10	8.19B	32.8k	-	-	🤗	-	View
Qwen3.5 2B (Reasoning)	Alibaba	10	2.27B	262k	$0.0	41	🤗		View
Qwen3 14B (Reasoning)	Alibaba	10	14.8B	32.8k	$0.4	63	🤗		View
Nanbeige4.1-3B	Nanbeige	10	3.93B	256k	-	-	🤗	-	View
Llama 4 Scout	Meta	10	109B 17B active at inference time	10.0M	$0.2	108	🤗	+6	View
Qwen3 VL 30B A3B Instruct	Alibaba	10	30B 3B active at inference time	256k	$0.2	112	🤗		View
Hermes 4 - Llama-3.1 70B (Reasoning)	Nous Research	10	70.6B	128k	$0.2	71	🤗		View
Ministral 3 14B	Mistral	10	14B	256k	$0.2	93	🤗		View
DeepSeek R1 Distill Llama 70B	DeepSeek	10	70B	128k	$0.7	50	🤗		View
DeepSeek R1 Distill Qwen 14B	DeepSeek	10	14B	128k	-	-	🤗	-	View
Falcon-H1R-7B	TII UAE	10	7B	256k	-	-	🤗	-	View
Ling-flash-2.0	InclusionAI	10	103B 6.1B active at inference time	128k	$0.2	55	🤗		View
Qwen3 Omni 30B A3B (Reasoning)	Alibaba	10	35.3B 3B active at inference time	65.5k	$0.3	84	🤗		View
Qwen2.5 Instruct 72B	Alibaba	10	72B	131k	$0.2	-	🤗		View
Step3 VL 10B	StepFun	9	10.2B	65.5k	-	-	🤗	-	View
Qwen3 30B A3B (Reasoning)	Alibaba	9	30.5B 3.3B active at inference time	32.8k	$0.1	110	🤗	+2	View
Devstral Small (Jul '25)	Mistral	9	24B	256k	$0.1	35	🤗		View
Gemma 4 E2B (Reasoning)	Google	9	5.1B 2.3B active at inference time	128k	-	-	🤗	-	View
QwQ 32B-Preview	Alibaba	9	32.8B	32.8k	-	-	🤗	-	View
GLM-4.5V (Reasoning)	Z AI	9	108B 12B active at inference time	64.0k	$0.7	26	🤗		View
Mistral Large 2 (Nov '24)	Mistral	9	123B	128k	$2.4	53	🤗		View
Mistral Small 3.2	Mistral	9	24B	128k	$0.1	140	🤗		View
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)	NVIDIA	9	253B	128k	$0.7	51	🤗		View
Qwen3 30B A3B 2507 Instruct	Alibaba	9	30.5B 3.3B active at inference time	262k	$0.2	144	🤗		View
ERNIE 4.5 300B A47B	Baidu	9	300B 47B active at inference time	131k	$0.4	-	🤗		View
Hermes 4 - Llama-3.1 405B (Reasoning)	Nous Research	9	406B	128k	$1.2	41	🤗		View
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)	NVIDIA	9	13.2B	128k	$0.2	284	🤗		View
Ministral 3 8B	Mistral	9	8B	256k	$0.1	102	🤗		View
Gemma 4 E4B (Non-reasoning)	Google	9	8B 4.5B active at inference time	128k	-	-	🤗	-	View
Granite 4.1 30B	IBM	9	30B	131k	-	-	🤗	-	View
NVIDIA Nemotron Nano 9B V2 (Reasoning)	NVIDIA	9	9B	131k	$0.1	89	🤗		View
Hermes 4 - Llama-3.1 405B (Non-reasoning)	Nous Research	9	406B	128k	$1.2	42	🤗		View
NVIDIA Nemotron 3 Nano 4B	NVIDIA	9	3.97B	262k	-	-	🤗	-	View
Qwen3.5 2B (Non-reasoning)	Alibaba	9	2.27B	262k	$0.0	31	🤗		View
Llama Nemotron Super 49B v1.5 (Non-reasoning)	NVIDIA	9	49B	128k	$0.1	50	🤗		View
Qwen3 32B (Non-reasoning)	Alibaba	9	32.8B	32.8k	$0.2	64	🤗	+4	View
Llama 3.3 Instruct 70B	Meta	9	70B	128k	$0.6	91	🤗	+18	View
Mistral Small 3.1	Mistral	9	24B	128k	$0.1	157	🤗		View
K2-V2 (low)	MBZUAI Institute of Foundation Models	9	70B	512k	-	-	🤗	-	View
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)	NVIDIA	9	4.51B	128k	-	-	🤗	-	View
Kimi Linear 48B A3B Instruct	Kimi	9	49.1B 3B active at inference time	1.00M	-	-	🤗	-	View
Llama 3.1 Instruct 405B	Meta	9	405B	128k	$3.1	64	🤗		View
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)	NVIDIA	8	49B	128k	-	-	🤗	-	View
Qwen3 VL 8B Instruct	Alibaba	8	8.77B	256k	$0.2	121	🤗		View
Qwen3 4B (Reasoning)	Alibaba	8	4.02B	32.0k	$0.2	-	🤗		View
Llama 3.1 Tulu3 405B	Allen Institute for AI	8	405B	128k	-	-	🤗	-	View
Ring-flash-2.0	InclusionAI	8	103B 6.1B active at inference time	128k	$0.2	-	🤗		View
Pixtral Large	Mistral	8	124B	128k	$2.4	50	🤗		View
Olmo 3.1 32B Think	Allen Institute for AI	8	32.2B	65.5k	-	-	🤗		View
Grok 2 (Dec '24)	xAI	8	270B	131k	-	-	🤗	-	View
Qwen3 VL 4B (Reasoning)	Alibaba	8	4.44B	256k	-	-	🤗	-	View
Command A	Cohere	8	111B	256k	$3.3	74	🤗		View
Llama 3.1 Nemotron Instruct 70B	NVIDIA	8	70B	128k	$1.2	299	🤗		View
Qwen2.5 Instruct 32B	Alibaba	7	32B	128k	-	-	🤗	-	View
Qwen3 8B (Reasoning)	Alibaba	7	8.19B	131k	$0.2	38	🤗		View
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)	NVIDIA	7	31.6B 3.6B active at inference time	1.00M	$0.1	87	🤗		View
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)	NVIDIA	7	9B	131k	$0.1	142	🤗		View
Mistral Large 2 (Jul '24)	Mistral	7	123B	128k	$2.4	-	🤗		View
Qwen3 4B 2507 Instruct	Alibaba	7	4.02B	262k	-	-	🤗	-	View
Qwen2.5 Coder Instruct 32B	Alibaba	7	32B	131k	-	-	🤗	-	View
Qwen3 14B (Non-reasoning)	Alibaba	7	14.8B	32.8k	$0.3	63	🤗		View
GLM-4.5V (Non-reasoning)	Z AI	7	108B 12B active at inference time	64.0k	$0.7	34	🤗		View
Mistral Small 3	Mistral	7	24B	32.0k	$0.1	152	🤗		View
Hermes 4 - Llama-3.1 70B (Non-reasoning)	Nous Research	7	70.6B	128k	$0.2	72	🤗		View
Qwen3 30B A3B (Non-reasoning)	Alibaba	7	30.5B 3.3B active at inference time	32.8k	$0.1	108	🤗		View
DeepSeek-V2.5 (Dec '24)	DeepSeek	7	236B 21B active at inference time	128k	-	-	🤗	-	View
Qwen3 4B (Non-reasoning)	Alibaba	7	4.02B	32.0k	$0.1	-	🤗		View
Llama 3.1 Instruct 70B	Meta	7	70B	128k	$0.6	31	🤗		View
Granite 4.1 8B	IBM	7	8B	131k	$0.1	122	🤗		View
Sarvam 30B (high)	Sarvam	7	32.2B 2.4B active at inference time	65.5k	$0.0	165	🤗		View
DeepSeek-V2.5	DeepSeek	7	236B 21B active at inference time	128k	-	-	🤗	-	View
Olmo 3.1 32B Instruct	Allen Institute for AI	6	32.2B	65.5k	-	-	🤗	-	View
DeepSeek R1 Distill Llama 8B	DeepSeek	6	8B	128k	-	-	🤗	-	View
Gemma 4 E2B (Non-reasoning)	Google	6	5.1B 2.3B active at inference time	128k	-	-	🤗	-	View
Olmo 3 32B Think	Allen Institute for AI	6	32.2B	65.5k	-	-	🤗	-	View
R1 1776	Perplexity	6	671B 37B active at inference time	128k	-	-	🤗	-	View
Llama 3.2 Instruct 90B (Vision)	Meta	6	90B	128k	$1.4	58	🤗		View
Solar Mini	Upstage	6	10.7B	4.10k	$0.1	-	🤗		View
Llama 3.1 Instruct 8B	Meta	6	8B	128k	$0.1	153	🤗	+12	View
Grok-1	xAI	6	314B 78B active at inference time	8.19k	-	-	🤗	-	View
Qwen2 Instruct 72B	Alibaba	6	72B	131k	-	-	🤗	-	View
EXAONE 4.0 32B (Non-reasoning)	LG AI Research	6	32B	131k	-	-	🤗	-	View
Ministral 3 3B	Mistral	6	3B	256k	$0.1	180	🤗		View
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)	Nous Research	5	24B	32.0k	-	-	🤗	-	View
Jamba 1.7 Large	AI21 Labs	5	398B 94B active at inference time	256k	$2.6	59	🤗		View
Granite 4.0 H Small	IBM	5	32B 9B active at inference time	128k	$0.1	386	🤗		View
Jamba 1.5 Large	AI21 Labs	5	398B 94B active at inference time	256k	$2.6	-	🤗		View
Qwen3 Omni 30B A3B Instruct	Alibaba	5	35.3B 3B active at inference time	65.5k	$0.3	95	🤗		View
Hermes 3 - Llama-3.1 70B	Nous Research	5	70.6B	128k	$0.3	32	🤗		View
Qwen3 8B (Non-reasoning)	Alibaba	5	8.19B	32.8k	$0.2	39	🤗		View
DeepSeek-Coder-V2	DeepSeek	5	236B 21B active at inference time	128k	-	-	🤗	-	View
OLMo 2 32B	Allen Institute for AI	5	32.2B	4.10k	-	-	🤗	-	View
Jamba 1.6 Large	AI21 Labs	5	398B 94B active at inference time	256k	$2.6	60	🤗		View
Qwen3.5 0.8B (Reasoning)	Alibaba	5	0.873B	262k	$0.0	32	🤗		View
LFM2 24B A2B	Liquid AI	5	23.8B 2.3B active at inference time	32.8k	$0.0	127	🤗		View
Phi-4	Microsoft	5	14B	16.0k	$0.2	40	🤗		View
Gemma 3 27B Instruct	Google	5	27.4B	128k	$0.1	-	🤗	+3	View
Mistral Small (Sep '24)	Mistral	5	22B	32.8k	$0.2	158	🤗		View
Phi-3 Mini Instruct 3.8B	Microsoft	5	3.8B	4.10k	-	-	🤗	-	View
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)	NVIDIA	5	13.2B	128k	$0.2	212	🤗		View
Gemma 3n E4B Instruct Preview (May '25)	Google	5	8.39B 4B active at inference time	32.0k	-	-	🤗	-	View
Phi-4 Multimodal Instruct	Microsoft	5	5.6B	128k	-	16	🤗		View
Qwen2.5 Coder Instruct 7B	Alibaba	4	7.62B	131k	-	-	🤗	-	View
Qwen3.5 0.8B (Non-reasoning)	Alibaba	4	0.873B	262k	$0.0	35	🤗		View
Mixtral 8x22B Instruct	Mistral	4	141B 39B active at inference time	65.4k	-	-	🤗	-	View
Llama 2 Chat 7B	Meta	4	7B	4.10k	$0.1	-	🤗		View
Llama 3.2 Instruct 3B	Meta	4	3B	128k	$0.1	51	🤗		View
MiniCPM-V 4.6 1.3B	OpenBMB	4	1.3B	262k	-	-	🤗	-	View
Jamba Reasoning 3B	AI21 Labs	4	3B	262k	-	-	🤗	-	View
Qwen3 VL 4B Instruct	Alibaba	4	4.44B	256k	-	-	🤗	-	View
Qwen1.5 Chat 110B	Alibaba	4	110B	32.0k	-	-	🤗	-	View
Reka Flash 3	Reka AI	4	21B	128k	$0.3	-	🤗		View
Olmo 3 7B Think	Allen Institute for AI	4	7B	65.5k	-	-	🤗	-	View
OLMo 2 7B	Allen Institute for AI	4	7.3B	4.10k	-	-	🤗	-	View
Molmo 7B-D	Allen Institute for AI	4	8.02B	4.10k	-	-	🤗	-	View
Ling-mini-2.0	InclusionAI	4	16.3B 1.4B active at inference time	131k	-	-	🤗	-	View
DeepSeek R1 Distill Qwen 1.5B	DeepSeek	4	1.5B	128k	-	-	🤗	-	View
DeepSeek-V2-Chat	DeepSeek	4	236B 21B active at inference time	128k	-	-	🤗	-	View
Llama 3 Instruct 70B	Meta	3	70B	8.19k	$0.9	-	🤗		View
Arctic Instruct	Snowflake	3	480B 17B active at inference time	4.00k	-	-	🤗	-	View
Qwen Chat 72B	Alibaba	3	72B	33.8k	-	-	🤗	-	View
Gemma 3 12B Instruct	Google	3	12.2B	128k	$0.1	-	🤗	+2	View
Llama 3.2 Instruct 11B (Vision)	Meta	3	11B	128k	$0.2	51	🤗		View
Granite 4.1 3B	IBM	3	3B	131k	-	-	🤗	-	View
DeepSeek Coder V2 Lite Instruct	DeepSeek	3	16B 2.4B active at inference time	128k	-	-	🤗	-	View
Sarvam M (Reasoning)	Sarvam	3	23.6B	32.8k	-	-	🤗		View
Phi-4 Mini Instruct	Microsoft	3	3.84B	128k	-	45	🤗		View
Llama 2 Chat 70B	Meta	3	70B	4.10k	-	-	🤗	-	View
DeepSeek LLM 67B Chat (V1)	DeepSeek	3	7B	4.10k	-	-	🤗	-	View
Llama 2 Chat 13B	Meta	3	13B	4.10k	-	-	🤗	-	View
Command-R+ (Apr '24)	Cohere	3	104B	128k	$4.2	-	🤗		View
OpenChat 3.5 (1210)	OpenChat	3	7B	8.19k	-	-	🤗	-	View
DBRX Instruct	Databricks	3	132B 36B active at inference time	32.8k	-	-	🤗	-	View
Exaone 4.0 1.2B (Reasoning)	LG AI Research	3	1.28B	64.0k	-	-	🤗	-	View
Olmo 3 7B Instruct	Allen Institute for AI	3	7B	65.5k	$0.1	-	🤗		View
Exaone 4.0 1.2B (Non-reasoning)	LG AI Research	3	1.28B	64.0k	-	-	🤗	-	View
LFM2.5-1.2B-Thinking	Liquid AI	3	1.17B	32.0k	-	-	🤗	-	View
Jamba 1.7 Mini	AI21 Labs	3	52B 12B active at inference time	258k	-	-	🤗	-	View
LFM2 2.6B	Liquid AI	3	2.57B	32.8k	-	338	🤗		View
LFM2.5-1.2B-Instruct	Liquid AI	3	1.17B	32.0k	-	492	🤗		View
Jamba 1.5 Mini	AI21 Labs	3	52B 12B active at inference time	256k	$0.2	-	🤗		View
Granite 4.0 H 1B	IBM	3	1.5B	128k	-	-	🤗	-	View
Qwen3 1.7B (Reasoning)	Alibaba	3	2.03B	32.0k	$0.2	-	🤗		View
Jamba 1.6 Mini	AI21 Labs	3	52B 12B active at inference time	256k	$0.2	181	🤗		View
Mixtral 8x7B Instruct	Mistral	2	46.7B 12.9B active at inference time	32.8k	$0.5	-	🤗		View
Gemma 3 270M	Google	2	0.268B	32.0k	-	-	🤗	-	View
Apertus 70B Instruct	Swiss AI Initiative	2	70B	65.5k	$1.0	-	🤗		View
Granite 4.0 Micro	IBM	2	3B	128k	-	-	🤗	-	View
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)	Nous Research	2	8B	128k	-	-	🤗	-	View
Llama 65B	Meta	2	65B	2.05k	-	-	🤗	-	View
Qwen Chat 14B	Alibaba	2	14B	8.19k	-	-	🤗	-	View
Mistral 7B Instruct	Mistral	2	7B	8.19k	$0.2	99	🤗		View
Command-R (Mar '24)	Cohere	2	35B	128k	$0.6	-	🤗		View
Granite 4.0 1B	IBM	2	1.6B	128k	-	-	🤗	-	View
Molmo2-8B	Allen Institute for AI	2	8.66B	36.9k	-	-	🤗	-	View
LFM2 8B A1B	Liquid AI	2	8.34B 1.5B active at inference time	32.8k	-	-	🤗		View
Granite 3.3 8B (Non-reasoning)	IBM	2	8.17B	128k	$0.1	351	🤗		View
Qwen3 1.7B (Non-reasoning)	Alibaba	2	2.03B	32.0k	$0.1	-	🤗		View
Qwen3 0.6B (Reasoning)	Alibaba	1	0.752B	32.0k	$0.2	-	🤗		View
Llama 3 Instruct 8B	Meta	1	8B	8.19k	$0.1	-	🤗		View
Gemma 3n E4B Instruct	Google	1	8.39B 4B active at inference time	32.0k	$0.0	54	🤗		View
LFM2 1.2B	Liquid AI	1	1.17B	32.8k	-	439	🤗		View
Gemma 3 4B Instruct	Google	1	4.3B	128k	$0.0	-	🤗		View
Llama 3.2 Instruct 1B	Meta	1	1B	128k	$0.1	84	🤗		View
LFM2.5-VL-1.6B	Liquid AI	1	1.6B	32.0k	-	425	🤗		View
Granite 4.0 H 350M	IBM	1	0.34B	32.8k	-	-	🤗	-	View
Granite 4.0 350M	IBM	1	0.35B	32.8k	-	-	🤗	-	View
Apertus 8B Instruct	Swiss AI Initiative	1	8B	65.5k	$0.1	-	🤗		View
Tiny Aya Global	Cohere	1	3.35B	8.19k	-	-	🤗		View
Gemma 3 1B Instruct	Google	1	1B	32.0k	-	-	🤗		View
Gemma 3n E2B Instruct	Google	1	5.98B 2B active at inference time	32.0k	-	-	🤗		View
Qwen3 0.6B (Non-reasoning)	Alibaba	1	0.752B	32.0k	$0.1	-	🤗		View
EXAONE 4.5 33B (Non-reasoning)	LG AI Research	-	34.4B	262k	-	-	🤗	-	View
Cogito v2.1 (Reasoning)	Deep Cogito	-	671B 37B active at inference time	128k	$1.3	91	🤗		View

Comparison of Open Source Models

Openness

Intelligence

Total Parameters

Openness

Artificial Analysis Openness Index: Score

Open Source Progress

Progress in Open Weights vs. Proprietary Intelligence

Artificial Analysis Intelligence Index

Open Weights

Open Source Language Models Intelligence By Lab Over Time

Artificial Analysis Intelligence Index

Open Source Models Intelligence By Size Over Time

Artificial Analysis Intelligence Index

Model Size Classifications

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Size

Intelligence Index By Model Size

Artificial Analysis Intelligence Index

Open Weights

Model Size Classifications

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