중형 오픈 웨이트 AI 모델 비교(40B~150B)

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

파라미터 수가 40B~150B개인 오픈 웨이트 AI 모델입니다.

웨이트를 다운로드할 수 있는 모델을 오픈 웨이트 모델(흔히 오픈 소스라고도 함)로 간주합니다. 자체 인프라에서 호스팅할 수 있으며 미세 조정 등을 통해 모델을 맞춤 설정할 수 있습니다.

방법론을 비롯한 자세한 내용은 FAQ에서 확인하세요.

Qwen3.5 122B A10B과

Mistral Medium 3.5은 파라미터 수가 40B~150B개인 중형 오픈 웨이트 모델 중 지능이 가장 높으며

Qwen3.5 122B A10B과

NVIDIA Nemotron 3 Super이 뒤를 잇습니다.

주요 내용

개방성

Artificial Analysis Openness Index · Higher is better

지능

Artificial Analysis Intelligence Index · Higher is better

개방성

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

지능

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

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.

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

GDPval-AA v2

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

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

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

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

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.

크기

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 Index vs. Active Parameters

Artificial Analysis Intelligence Index · Active parameters at inference time

Most attractive quadrant

Pareto line

Reasoning models are indicated by a lightbulb icon

Intelligence Index vs. Total Parameters

Artificial Analysis Intelligence Index · Size in parameters (billions)

Most attractive quadrant

Pareto line

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.

컨텍스트 창

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).

상세 정보

							웨이트		제공업체 벤치마크
Qwen3.5 122B A10B (Reasoning)	Alibaba	32	125B 추론 시 10B 활성	262k	$0.7	125	🤗	+2	보기
Mistral Medium 3.5	Mistral	30	128B	256k	$1.2	134	🤗		보기
Qwen3.5 122B A10B (Non-reasoning)	Alibaba	28	125B 추론 시 10B 활성	262k	$0.7	140	🤗		보기
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)	NVIDIA	25	120.6B 추론 시 12.7B 활성	1M	$0.3	143	🤗		보기
gpt-oss-120b (high)	OpenAI	24	117B 추론 시 5.1B 활성	131k	$0.2	185	🤗	+18	보기
Qwen3 Coder Next	Alibaba	21	79.7B 추론 시 3B 활성	256k	$0.4	133	🤗		보기
Mistral Small 4 (Reasoning)	Mistral	20	119B 추론 시 6.5B 활성	256k	$0.2	158	🤗		보기
Devstral 2	Mistral	19	125B	256k	-	43	🤗		보기
HyperNova 60B 2605	Multiverse Computing	18	58.7B 추론 시 4.8B 활성	131k	$0.1	349	🤗		보기
K2 Think V2	MBZUAI Institute of Foundation Models	17	70B	262k	-	-	🤗	-	보기
LongCat Flash Lite	LongCat	17	68.5B 추론 시 3B 활성	256k	-	-	🤗	-	보기
Qwen3 Next 80B A3B (Reasoning)	Alibaba	17	80B 추론 시 3B 활성	262k	$1.1	205	🤗	+2	보기

중형 오픈 웨이트 AI 모델 비교(40B~150B)

개방성

지능

총 파라미터 수

개방성

Artificial Analysis Openness Index: Score

지능

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

크기

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

컨텍스트 창

Context Window

Context Window for RAG

Context Window

상세 정보