Comparison of Open Source Models

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.

Alibaba logo Qwen3 235B 2507 (Reasoning) and DeepSeek logo DeepSeek R1 0528 are the highest intelligence open source models, followed by Z AI logo GLM-4.5 & LG AI Research logo EXAONE 4.0 32B (Reasoning).

Highlights

Intelligence

Artificial Analysis Intelligence Index; Higher is better

Loading chart...

Total Parameters

Trainable parameters in billions

Loading chart...

Navigation

Open Source Progress Size Context Window

Further details

						Weights		Provider Benchmarks
Qwen3 235B A22B 2507 (Reasoning) Alibaba	69	235B (22B active at inference time)	132k	$2.6	65	Not available	+3 more	View
DeepSeek R1 0528 (May '25) DeepSeek	68	685B (37B active at inference time)	128k	$1.0	23	🤗	+11 more	View
GLM-4.5 Z AI	66	355B (32B active at inference time)	128k	$1.0	88	🤗	+2 more	View
EXAONE 4.0 32B (Reasoning) LG AI Research	64	32B	131k	$0.7	99	🤗		View
Llama Nemotron Super 49B v1.5 (Reasoning) NVIDIA	64	49B	128k	-	-	🤗	?	View
Qwen3 30B A3B 2507 (Reasoning) Alibaba	63	30.5B	128k	$0.8	109	🤗		View
MiniMax M1 80k MiniMax	63	456B (45.9B active at inference time)	1.00M	$0.8	25	🤗		View
Qwen3 235B A22B (Reasoning) Alibaba	62	235B (22B active at inference time)	128k	$2.6	37	🤗	+5 more	View
MiniMax M1 40k MiniMax	61	456B (45.9B active at inference time)	1.00M	$0.8	26	🤗		View
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) NVIDIA	61	253B	128k	$0.9	43	🤗		View
Qwen3 235B A22B 2507 (Non-reasoning) Alibaba	60	235B (22.0B active at inference time)	256k	$1.2	39	🤗	+4 more	View
DeepSeek R1 (Jan '25) DeepSeek	60	685B (37B active at inference time)	128k	$2.0	-	🤗	+10 more	View
GLM-4.5-Air Z AI	60	-	128k	$0.4	161	🤗		View
Qwen3 32B (Reasoning) Alibaba	59	32.8B	128k	$2.6	65	🤗	+6 more	View
QwQ 32B Alibaba	58	32.8B	131k	$0.5	55	🤗	+3 more	View
Kimi K2 Moonshot AI	58	1.0KB (32B active at inference time)	128k	$1.1	47	🤗	+6 more	View
Qwen3 30B A3B 2507 (Non-reasoning) Alibaba	57	30.5B	128k	$0.3	107	🤗		View
Qwen3 14B (Reasoning) Alibaba	56	14.8B	128k	$1.3	59	🤗		View
Qwen3 30B A3B (Reasoning) Alibaba	56	30.5B (3.3B active at inference time)	128k	$0.8	86	🤗	+4 more	View
Magistral Small Mistral	55	23.6B	128k	$0.8	195	🤗		View
Qwen3 Coder 480B A35B Alibaba	54	480B (35.0B active at inference time)	262k	$3.0	52	🤗	+7 more	View
DeepSeek V3 0324 (Mar '25) DeepSeek	53	671B (37B active at inference time)	128k	$0.5	22	🤗	+10 more	View
DeepSeek R1 0528 Qwen3 8B DeepSeek	52	8.19B	128k	$0.1	92	🤗		View
DeepSeek R1 Distill Qwen 32B DeepSeek	52	32B	128k	$0.3	33	🤗		View
Qwen3 8B (Reasoning) Alibaba	51	8.19B	128k	$0.7	99	🤗		View
Llama 3.3 Nemotron Super 49B v1 (Reasoning) NVIDIA	51	49B	128k	-	-	🤗	-	View
EXAONE 4.0 32B LG AI Research	51	32B	131k	$0.7	89	Not available		View
Llama 4 Maverick Meta	51	402B (17B active at inference time)	1.00M	$0.4	171	🤗	+11 more	View
DeepSeek R1 Distill Qwen 14B DeepSeek	49	14B	128k	$0.2	86	🤗		View
DeepSeek R1 Distill Llama 70B DeepSeek	48	70B	128k	$0.8	77	🤗	+6 more	View
Qwen3 4B (Reasoning) Alibaba	47	4.02B	32.0k	$0.4	105	🤗		View
Reka Flash 3 Reka AI	47	21B	128k	$0.3	56	🤗		View
Qwen3 235B A22B Alibaba	47	235B (22B active at inference time)	128k	$1.2	38	🤗	+4 more	View
DeepSeek V3 (Dec '24) DeepSeek	46	671B (37B active at inference time)	128k	$0.5	-	🤗	+6 more	View
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) NVIDIA	45	4.51B	128k	-	-	🤗	-	View
Qwen3 32B Alibaba	44	32.8B	128k	$1.2	65	🤗	+6 more	View
Llama 4 Scout Meta	43	109B (17B active at inference time)	10.0M	$0.2	130	🤗	+9 more	View
QwQ 32B-Preview Alibaba	43	32.8B	32.8k	$0.7	51	🤗		View
Qwen3 30B A3B Alibaba	43	30.5B (3.3B active at inference time)	128k	$0.3	80	🤗		View
Mistral Small 3.2 Mistral	42	24B	128k	$0.1	181	🤗		View
Llama 3.3 Instruct 70B Meta	41	70B	128k	$0.6	92	🤗	+15 more	View
Qwen3 14B Alibaba	41	14.8B	128k	$0.6	60	🤗		View
Llama 3.1 Instruct 405B Meta	40	405B	128k	$3.3	34	🤗	+11 more	View
Qwen2.5 Instruct 72B Alibaba	40	72B	131k	-	58	🤗	+3 more	View
MiniMax-Text-01 MiniMax	40	456B (45.9B active at inference time)	4.00M	$0.4	35	🤗		View
Phi-4 Microsoft Azure	40	14B	16.0k	$0.2	42	🤗		View
Command A Cohere	40	111B	256k	$4.4	59	🤗		View
Llama 3.1 Tulu3 405B Allen Institute for AI	40	405B	128k	-	-	🤗	-	View
Llama 3.3 Nemotron Super 49B v1 NVIDIA	39	49B	128k	-	-	🤗	-	View
Mistral Large 2 (Nov '24) Mistral	38	123B	128k	$3.0	21	🤗		View
Llama Nemotron Super 49B v1.5 NVIDIA	38	49B	128k	-	-	🤗	?	View
Qwen3 1.7B (Reasoning) Alibaba	38	2.03B	32.0k	$0.4	138	🤗		View
Gemma 3 27B Instruct Google	38	27.4B	128k	-	53	🤗		View
Pixtral Large Mistral	37	124B	128k	$3.0	84	🤗		View
Qwen2.5 Instruct 32B Alibaba	37	32B	128k	$0.1	-	🤗		View
Llama 3.1 Nemotron Instruct 70B NVIDIA	37	70B	128k	$0.2	48	🤗		View
Qwen3 8B Alibaba	37	8.19B	128k	$0.3	100	🤗		View
Mistral Large 2 (Jul '24) Mistral	37	123B	128k	$3.0	68	🤗		View
Qwen2.5 Coder Instruct 32B Alibaba	36	32B	131k	$0.1	52	🤗	+1 more	View
Llama 3.1 Instruct 70B Meta	35	70B	128k	$0.8	64	🤗	+10 more	View
Mistral Small 3.1 Mistral	35	24B	128k	$0.1	138	🤗		View
Mistral Small 3 Mistral	35	24B	32.0k	$0.1	75	🤗		View
DeepSeek-V2.5 (Dec '24) DeepSeek	35	236B (21B active at inference time)	128k	$0.2	-	🤗		View
Qwen3 4B Alibaba	35	4.02B	32.0k	$0.2	106	🤗		View
DeepSeek-V2.5 DeepSeek	35	236B (21B active at inference time)	128k	$0.2	-	🤗		View
Devstral Small (May '25) Mistral	34	23.6B	256k	$0.1	95	🤗		View
DeepSeek R1 Distill Llama 8B DeepSeek	34	8B	128k	$0.0	41	🤗		View
Gemma 3 12B Instruct Google	34	12.2B	128k	$0.1	-	🤗		View
R1 1776 Perplexity	34	671B (37B active at inference time)	128k	$3.5	-	🤗		View
Llama 3.2 Instruct 90B (Vision) Meta	33	90B	128k	$0.5	34	🤗		View
Solar Mini Upstage	33	10.7B	4.10k	$0.1	91	🤗		View
Grok-1 xAI	33	314B (78B active at inference time)	8.19k	-	-	🤗	-	View
Qwen2 Instruct 72B Alibaba	33	72B	131k	-	31	🤗		View
Devstral Small (Jul '25) Mistral	32	24B	256k	$0.1	160	🤗		View
Gemma 2 27B Google	32	27.2B	8.19k	$0.8	-	🤗		View
DeepHermes 3 - Mistral 24B Preview Nous Research	30	24B	32.0k	-	-	🤗	-	View
Jamba 1.7 Large AI21 Labs	30	398B (94.0B active at inference time)	256k	$3.5	55	🤗		View
Jamba 1.5 Large AI21 Labs	29	398B (94B active at inference time)	256k	$3.5	-	🤗		View
Hermes 3 - Llama-3.1 70B Nous Research	29	70.6B	128k	$0.1	37	🤗		View
DeepSeek-Coder-V2 DeepSeek	29	236B (21B active at inference time)	128k	$0.2	-	🤗		View
Jamba 1.6 Large AI21 Labs	29	398B (94B active at inference time)	256k	$3.5	51	🤗		View
Gemma 3n E4B Instruct Google	28	8.39B (4.0B active at inference time)	32.0k	$0.0	69	🤗		View
Llama 3 Instruct 70B Meta	27	70B	8.19k	$0.8	49	🤗	+7 more	View
Mistral Small (Sep '24) Mistral	27	22B	32.8k	$0.3	93	🤗		View
Gemma 3n E4B Instruct Preview (May '25) Google	27	8.39B (4B active at inference time)	32.0k	-	-	🤗	-	View
Phi-4 Multimodal Instruct Microsoft Azure	27	5.6B	128k	-	23	🤗		View
Qwen2.5 Coder Instruct 7B Alibaba	27	7.62B	131k	-	-	🤗	-	View
Mixtral 8x22B Instruct Mistral	26	141B (39B active at inference time)	65.4k	$3.0	57	🤗		View
Phi-4 Mini Instruct Microsoft Azure	26	3.84B	128k	-	57	🤗		View
Granite 3.3 Instruct 8B IBM	26	8.17B	128k	-	-	🤗	-	View
Gemma 3 4B Instruct Google	25	4.3B	128k	$0.0	-	🤗		View
Llama 3.2 Instruct 11B (Vision) Meta	25	11B	128k	$0.1	110	🤗		View
Qwen3 1.7B Alibaba	25	2.03B	32.0k	$0.2	140	🤗		View
Qwen1.5 Chat 110B Alibaba	25	110B	32.0k	-	24	🤗		View
Phi-3 Medium Instruct 14B Microsoft Azure	25	14B	128k	$0.3	53	🤗		View
Llama 3.1 Instruct 8B Meta	24	8B	128k	$0.1	202	🤗	+14 more	View
Pixtral 12B (2409) Mistral	23	12B	128k	$0.1	102	🤗		View
Qwen3 0.6B (Reasoning) Alibaba	23	0.752B	32.0k	$0.4	228	🤗		View
DeepSeek-V2-Chat DeepSeek	23	236B (21B active at inference time)	128k	$0.2	-	🤗		View
Gemma 3n E2B Instruct Google	22	5.98B (2.0B active at inference time)	32.0k	-	52	🤗		View
Ministral 8B Mistral	22	8B	128k	$0.1	205	🤗		View
Gemma 2 9B Google	22	9B	8.19k	$0.2	-	🤗		View
Phi-3 Mini Instruct 3.8B Microsoft Azure	22	3.8B	4.10k	-	-	🤗	-	View
Arctic Instruct Snowflake	22	480B (17B active at inference time)	4.00k	-	-	🤗	-	View
Qwen Chat 72B Alibaba	22	72B	33.8k	$1.0	-	🤗		View
Command-R+ (Aug '24) Cohere	21	104B	128k	$4.4	48	🤗		View
Llama 3 Instruct 8B Meta	21	8B	8.19k	$0.1	91	🤗	+4 more	View
DeepSeek Coder V2 Lite Instruct DeepSeek	20	16B (2.4B active at inference time)	128k	-	-	🤗	-	View
Codestral (May '24) Mistral	20	22B	32.8k	$0.3	-	🤗		View
Aya Expanse 32B Cohere	20	32B	128k	$0.8	121	🤗		View
Llama 2 Chat 70B Meta	20	70B	4.10k	-	-	🤗	-	View
DeepSeek LLM 67B Chat (V1) DeepSeek	20	7B	4.10k	-	-	🤗	-	View
Llama 2 Chat 13B Meta	20	13B	4.10k	-	-	🤗	-	View
Command-R+ (Apr '24) Cohere	20	104B	128k	$6.0	60	🤗		View
OpenChat 3.5 (1210) OpenChat	20	7B	8.19k	-	-	🤗	-	View
DBRX Instruct Databricks	20	132B (36B active at inference time)	32.8k	-	-	🤗	-	View
Mistral NeMo Mistral	20	12B	128k	$0.1	175	🤗	+1 more	View
Llama 3.2 Instruct 3B Meta	20	3B	128k	$0.0	142	🤗	+4 more	View
DeepSeek R1 Distill Qwen 1.5B DeepSeek	19	1.5B	128k	-	-	🤗	-	View
Jamba 1.5 Mini AI21 Labs	18	52B (12B active at inference time)	256k	$0.3	-	🤗		View
Jamba 1.7 Mini AI21 Labs	18	52B (12.0B active at inference time)	258k	$0.3	165	🤗		View
Jamba 1.6 Mini AI21 Labs	18	52B (12B active at inference time)	256k	$0.3	164	🤗		View
Mixtral 8x7B Instruct Mistral	17	46.7B (12.9B active at inference time)	32.8k	$0.7	80	🤗	? +2 more	View
Qwen3 0.6B Alibaba	17	0.752B	32.0k	$0.2	230	🤗		View
DeepHermes 3 - Llama-3.1 8B Preview Nous Research	16	8B	128k	-	-	🤗	-	View
Aya Expanse 8B Cohere	16	8B	8.00k	$0.8	168	🤗		View
Command-R (Aug '24) Cohere	15	32B	128k	$0.3	74	🤗		View
Command-R (Mar '24) Cohere	15	35B	128k	$0.8	174	🤗		View
Codestral-Mamba Mistral	14	7B	256k	-	-	🤗	-	View
Gemma 3 1B Instruct Google	13	1B	32.0k	-	-	🤗	?	View
Mistral 7B Instruct Mistral	10	7B	8.19k	$0.3	122	🤗	? +3 more	View
Llama 3.2 Instruct 1B Meta	10	1B	128k	$0.1	153	🤗		View
Llama 2 Chat 7B Meta	8	7B	4.10k	$0.1	133	🤗		View

Comparison of Open Source Models