Comparisons of Medium Open Source AI Models (40B-150B)

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

Open source AI models with between 40B to 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.

Qwen3.5 122B A10B and

Mistral Medium 3.5 are the highest intelligence Medium open source models, defined as those with 40B-150B parameters, followed by

NVIDIA Nemotron 3 Super &

Qwen3.5 122B A10B.

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

Results claimed by AI Lab (not yet independently verified)

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

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

InclusionAI

LongCat

MBZUAI Institute of Foundation Models

Intelligence vs. Total Parameters

Artificial Analysis Intelligence Index · Size in parameters (billions)

Most attractive quadrant

Alibaba

InclusionAI

LongCat

MBZUAI Institute of Foundation Models

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
Qwen3.5 122B A10B (Reasoning) Alibaba	42	125B (10B active at inference time)	262k	$1.1	152	🤗	+2 more	View
Mistral Medium 3.5 Mistral	39	128B	256k	$3.0	154	🤗		View
NVIDIA Nemotron 3 Super 120B A12B (Reasoning) NVIDIA	36	120.6B (12.7B active at inference time)	1.00M	$0.4	225	🤗	+2 more	View
Qwen3.5 122B A10B (Non-reasoning) Alibaba	36	125B (10B active at inference time)	262k	$1.1	154	🤗		View
gpt-oss-120B (high) OpenAI	33	117B (5.1B active at inference time)	131k	$0.3	249	🤗	+22 more	View
Qwen3 Coder Next Alibaba	28	79.7B (3B active at inference time)	256k	$0.6	96	🤗	+1 more	View
Mistral Small 4 (Reasoning) Mistral	28	119B (6.5B active at inference time)	256k	$0.3	164	🤗		View
Qwen3 Next 80B A3B (Reasoning) Alibaba	27	80B (3B active at inference time)	262k	$1.9	154	🤗	+4 more	View
Ling 2.6 Flash InclusionAI	26	107B (7.4B active at inference time)	262k	$0.2	-	🤗		View
gpt-oss-120B (low) OpenAI	24	117B (5.1B active at inference time)	131k	$0.3	305	🤗	+18 more	View
K2 Think V2 MBZUAI Institute of Foundation Models	24	70B	262k	-	-	🤗	-	View
LongCat Flash Lite LongCat	24	68.5B (3B active at inference time)	256k	-	93	🤗		View
INTELLECT-3 Prime Intellect	22	107B (12B active at inference time)	131k	-	-	🤗	-	View
Devstral 2 Mistral	22	125B	256k	-	61	🤗		View
Solar Open 100B (Reasoning) Upstage	22	102B (12B active at inference time)	128k	-	-	🤗	-	View
K2-V2 (high) MBZUAI Institute of Foundation Models	21	70B	512k	-	-	🤗	-	View
Qwen3 Next 80B A3B Instruct Alibaba	20	80B (3B active at inference time)	262k	$0.9	157	🤗	+4 more	View
K2-V2 (medium) MBZUAI Institute of Foundation Models	19	70B	512k	-	-	🤗	-	View
Llama Nemotron Super 49B v1.5 (Reasoning) NVIDIA	19	49B	128k	$0.2	50	🤗		View
Mistral Small 4 (Non-reasoning) Mistral	19	119B (6.5B active at inference time)	256k	$0.3	147	🤗		View
Llama 3.3 Nemotron Super 49B v1 (Reasoning) NVIDIA	18	49B	128k	-	-	🤗	-	View
Sarvam 105B (high) Sarvam	18	106B (10.3B active at inference time)	128k	-	133	🤗		View
Hermes 4 - Llama-3.1 70B (Reasoning) Nous Research	16	70.6B	128k	$0.2	72	🤗		View
DeepSeek R1 Distill Llama 70B DeepSeek	16	70B	128k	$0.8	43	🤗		View
Ling-flash-2.0 InclusionAI	16	103B (6.1B active at inference time)	128k	$0.2	52	🤗		View
Llama Nemotron Super 49B v1.5 (Non-reasoning) NVIDIA	15	49B	128k	$0.2	50	🤗		View
Llama 3.3 Instruct 70B Meta	14	70B	128k	$0.6	84	🤗	+17 more	View
K2-V2 (low) MBZUAI Institute of Foundation Models	14	70B	512k	-	-	🤗	-	View
Kimi Linear 48B A3B Instruct Kimi	14	49.1B (3B active at inference time)	1.00M	-	-	🤗	-	View
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) NVIDIA	14	49B	128k	-	-	🤗	-	View
Ring-flash-2.0 InclusionAI	14	103B (6.1B active at inference time)	128k	$0.2	-	🤗		View
Llama 4 Scout Meta	14	109B (17B active at inference time)	10.0M	$0.3	120	🤗	+6 more	View
Command A Cohere	13	111B	256k	$4.4	37	🤗		View
Llama 3.1 Nemotron Instruct 70B NVIDIA	13	70B	128k	$1.2	298	🤗		View
Hermes 4 - Llama-3.1 70B (Non-reasoning) Nous Research	13	70.6B	128k	$0.2	74	🤗		View
Llama 3.2 Instruct 90B (Vision) Meta	12	90B	128k	$1.4	59	🤗		View
Jamba 1.7 Mini AI21 Labs	8	52B (12B active at inference time)	258k	-	-	🤗	-	View
Apertus 70B Instruct Swiss AI Initiative	8	70B	65.5k	$1.3	-	🤗		View

Comparisons of Medium Open Source AI Models (40B-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