Artificial Analysis Openness Index
Openness Index
Openness Index
Openness Index
Artificial Analysis Openness Index: 점수
지수 구성 요소
Artificial Analysis Openness Index: 구성 요소
투명성 vs. 가용성
Artificial Analysis Openness Index: 모델 가용성 vs. 투명성
Openness Index vs. 출시일
Artificial Analysis Openness Index: 점수 vs. 출시일
개방성 vs. 지능
Artificial Analysis Openness Index vs. Intelligence Index
Openness Index 구성
채점 방법
각 구성 요소는 가장 적합한 개방성 유형에 따라 0~3점의 정성적 척도로 평가합니다. 공개된 모든 1차 정보를 바탕으로 모델을 평가합니다.
이 요소들을 통합해 Artificial Analysis Openness Index를 다음과 같이 산출합니다.
- 사전 학습과 사후 학습의 데이터 요소를 평균합니다(데이터 전체 6점)
- 모든 구성 요소의 점수를 합산합니다(최대 18/18점)
- 이 점수를 0~100 척도로 정규화합니다
타사 기반 모델에서 파생된 모델은 원본 모델의 라이선스나 제한적인 정보 공개의 영향을 받을 수 있습니다. 증분 또는 업데이트 릴리스는 새 릴리스에 대해 명시적으로 공개된 정보만 고려합니다(이전 릴리스와 동일한 구성 요소를 개발자가 명시할 수 있습니다).
Openness Index 순위표
개발사 | 모델 | Openness Index | Intelligence Index | 모델 가용성 | 모델 투명성 | 사전 학습 데이터 접근 | 사전 학습 데이터 라이선스 | 사후 학습 데이터 접근 | 사후 학습 데이터 라이선스 | |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 |  Institute of Foundation Models | K2 Think V2 | 88.89 | 11.50 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 2 | Institute of Foundation Models | K2-V2 (High) | 88.89 | 9.87 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 3 | Institute of Foundation Models | K2-V2 (Medium) | 88.89 | 9.02 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 4 | Institute of Foundation Models | K2-V2 (Low) | 88.89 | 7.31 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 5 |  Allen Institute for AI | Olmo 3.1 32B Think | 88.89 | 7.12 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 6 | Allen Institute for AI | Olmo 3.1 32B Instruct | 88.89 | 6.50 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 7 | Allen Institute for AI | Olmo 3 32B Think | 88.89 | 6.47 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 8 | Allen Institute for AI | OLMo 2 32B | 88.89 | 5.97 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 9 | Allen Institute for AI | Olmo 3 7B Think | 88.89 | 5.62 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 10 | Allen Institute for AI | OLMo 2 7B | 88.89 | 5.58 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 11 | Allen Institute for AI | Molmo 7B-D | 88.89 | 5.56 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 12 | Allen Institute for AI | Olmo 3 7B Instruct | 88.89 | 5.24 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 13 |  Swiss AI Initiative | Apertus 70B Instruct | 88.89 | 5.11 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 14 | Swiss AI Initiative | Apertus 8B Instruct | 88.89 | 4.83 | 6.00 | 10.00 | 3.00 | 1.00 | 3.00 | 1.00 |
| 15 |  NVIDIA | Nemotron 3.5 Super VL | 83.33 | 26.49 | 6.00 | 9.00 | 2.00 | 1.00 | 2.00 | 1.00 |
자주 묻는 질문
Artificial Analysis Openness Index는 모델 가중치, 라이선스, 학습 데이터, 학습 방법론, 학습 코드를 포함해 AI 모델이 얼마나 개방적으로 제공되고 투명하게 문서화되어 있는지를 측정하는 종합 점수입니다.
Artificial Analysis Openness Index는 모델 이용 가능성(가중치 접근 및 라이선스)과 모델 투명성(학습 데이터 접근 및 라이선스, 방법론 공개, 학습 파이프라인 공개)을 각각 0~3의 정성적 척도로 평가합니다. 데이터 점수는 사전 학습과 사후 학습의 평균을 내고 구성 요소 점수를 최대 18점까지 합산한 뒤 0~100 척도로 정규화합니다.
공개된 Openness Index 결과가 있는 모델 중 현재 K2 Think V2이 89로 가장 높은 점수를 기록하고 있습니다. 모델 보기
개방적이고 투명한 모델은 재현성, 독립 평가, 특정 사용 사례에 맞춘 사용자 지정, 공급자 종속 없는 상업적 이용을 지원합니다. Artificial Analysis Openness Index는 모델의 개방성을 하나의 비교 가능한 점수로 제공하여 모델을 선택할 때 지능, 속도, 가격과 함께 고려할 수 있게 합니다.
아닙니다. 오픈 웨이트는 모델 가중치를 사용할 수 있다는 뜻이지만 소스 코드, 학습 데이터, 학습 방법, 허용적인 라이선스까지 제공된다는 보장은 없습니다. Artificial Analysis Openness Index는 이러한 요소를 개별적으로 평가하여 접근 가능한 모델과 폭넓게 개방되고 투명한 모델을 구분합니다.
평가 살펴보기
Artificial Analysis Intelligence Index v4.3.2A composite benchmark aggregating ten challenging evaluations to provide a holistic measure of AI capabilities across mathematics, science, coding, and reasoning.
AA-Briefcase v1.1: Agentic Knowledge Work BenchmarkA private evaluation developed by Artificial Analysis for frontier agentic capability in long-horizon knowledge work, testing agents on realistic business workflows that require deliverables such as spreadsheets, presentations, and memos.
GDPval-AA v2.1 BenchmarkGDPval-AA v2.1 is Artificial Analysis' evaluation framework for OpenAI's GDPval dataset. It tests AI models on real-world tasks across 44 occupations and 9 major industries. Models are given shell access and web browsing capabilities in an agentic loop via Stirrup to solve tasks, with Elo ratings derived from blind pairwise comparisons.
AA-3D: Interactive 3D Experience BenchmarkA benchmark developed by Artificial Analysis for how well AI models build interactive 3D experiences. Models work as agents in an offline sandbox via Stirrup to turn a written brief into a three.js scene, with Elo ratings derived from blind pairwise votes.
APEX-Agents-AA BenchmarkArtificial Analysis' implementation of the APEX-Agents benchmark, testing AI agents on long-horizon, cross-application tasks in professional-services environments with realistic application tooling.
AA-AnalystAgent BenchmarkArtificial Analysis' data analysis benchmark, testing AI agents on their ability to work with spreadsheets and documents to answer quantitative questions a Business Analyst or Data Analyst would face day-to-day.
AutomationBench-AA: Agentic SaaS Workflow BenchmarkA benchmark measuring agentic task completion across simulated SaaS application environments, scoring the share of each task's objectives completed without guardrail violations.
Harvey LAB-AA v1.1 BenchmarkArtificial Analysis' implementation of Harvey's Legal Agent Benchmark (LAB), testing AI agents on real-world legal work from Harvey's dataset of 120 private tasks spanning 24 legal practice areas. v1.1, built in collaboration with Harvey, checks every deliverable against the task's source documents for hallucinations, so work that passes every rubric criterion but contains a material hallucination receives no credit. A panel of three judges grades each deliverable criterion-by-criterion.
GDP.pdf BenchmarkArtificial Analysis' implementation of Surge AI's GDP.pdf benchmark, testing whether language models can reason over long, real-world professional documents and satisfy detailed task-specific criteria.
EnterpriseOps-Gym-AA BenchmarkArtificial Analysis' independent implementation of ServiceNow's EnterpriseOps-Gym, an agentic benchmark testing whether LLM agents can complete stateful, multi-step enterprise workflows across eight business domains via live tool use, graded on the final state of the underlying databases.
Terminal-Bench 4.0 BenchmarkA harder 66-task benchmark of complex terminal work across software, machine learning, science, operations, security, hardware, and media, with recalibrated compute and time allowances and improved instructions, environments, and verifiers.
Terminal-Bench-Science 0.1 BenchmarkA 70-task benchmark of research workflows authored and reviewed by domain experts across the life, physical, earth, mathematical, and engineering sciences, each completed in a terminal and checked by its own set of tests.
FrontierCode 1.1 BenchmarkArtificial Analysis' implementation of Cognition's FrontierCode 1.1, a private agentic coding benchmark that tests models on completing coding tasks in a way that would actually get merged by maintainers of real-world repositories.
AA-PersonalityBench: AI Personality & Communication Style BenchmarkMeasures how models communicate rather than whether they are correct: 30 judged personality traits rolled up into 8 indexes, plus 21 measured communication characteristics.
AA-LCR v1.1: Long Context Reasoning BenchmarkA challenging benchmark measuring language models' ability to extract, reason about, and synthesize information from long-form documents ranging from 10k to 100k tokens (measured using the cl100k_base tokenizer).
AA-Omniscience: Knowledge and Hallucination BenchmarkA benchmark measuring factual recall and hallucination across various economically relevant domains.
SciCode BenchmarkA scientist-curated coding benchmark featuring 288 test set subproblems from 80 laboratory problems across 16 scientific disciplines.
Humanity's Last Exam BenchmarkA frontier-level benchmark with 2,500 expert-vetted questions across mathematics, sciences, and humanities, designed to be the final closed-ended academic evaluation.
CritPt BenchmarkA benchmark designed to test LLMs on research-level physics reasoning tasks, featuring 71 composite research challenges.
The most challenging 198 questions from GPQA, where PhD experts achieve 65% accuracy but skilled non-experts only reach 34% despite web access.
ITBench-AA BenchmarkArtificial Analysis' implementation of IBM's ITBench benchmark, testing AI agents on Kubernetes incident root-cause analysis from offline incident snapshots. The agent inspects alerts, events, traces, and topology and identifies the contributing-factor entities (deployments, pods, namespaces, network policies, etc.) responsible for the failure.
MMMU-Pro BenchmarkAn enhanced MMMU benchmark that eliminates shortcuts and guessing strategies to more rigorously test multimodal models across 30 academic disciplines.
IFBench BenchmarkA benchmark evaluating precise instruction-following generalization on 58 diverse, verifiable out-of-domain constraints that test models' ability to follow specific output requirements.
MLCR-AA: Medical Long Context Reasoning BenchmarkAn open benchmark from Wisedocs measuring how well models reason over long, fragmented medical records, performing the multi-document synthesis claims professionals rely on when reviewing insurance and healthcare cases.
HealthBench BenchmarkOpenAI's HealthBench: 5,000 health conversations graded against physician-written rubrics, from emergency referrals to global health.
HealthBench Professional BenchmarkOpenAI's HealthBench Professional: 525 clinician conversations covering consult, writing and research tasks, graded against physician-written rubrics.
𝜏³-Banking BenchmarkA fintech customer-support benchmark from the 𝜏-Knowledge framework that tests whether agents can navigate a large unstructured knowledge base and execute multi-step tool calls to resolve realistic banking workflows.
Terminal-Bench 2.1 BenchmarkA verified refresh of Terminal-Bench 2.0 — 89 curated tasks across software engineering, system administration, data processing, model training, and security, with environment and instruction fixes so scores reflect agent capability rather than environment gaps.
Terminal-Bench Hard BenchmarkAn agentic benchmark evaluating AI capabilities in terminal environments through software engineering, system administration, and data processing tasks.
𝜏²-Bench Telecom BenchmarkA dual-control conversational AI benchmark simulating technical support scenarios where both agent and user must coordinate actions to resolve telecom service issues.
MMLU-Pro BenchmarkAn enhanced version of MMLU with 12,000 graduate-level questions across 14 subject areas, featuring ten answer options and deeper reasoning requirements.
LiveCodeBench BenchmarkA contamination-free coding benchmark that continuously harvests fresh competitive programming problems from LeetCode, AtCoder, and CodeForces, evaluating code generation, self-repair, and execution.
MATH-500 BenchmarkA 500-problem subset from the MATH dataset, featuring competition-level mathematics across six domains including algebra, geometry, and number theory.
AIME 2025 BenchmarkAll 30 problems from the 2025 American Invitational Mathematics Examination, testing olympiad-level mathematical reasoning with integer answers from 000-999.
Global-MMLU-Lite BenchmarkA lightweight, multilingual version of MMLU, designed to evaluate knowledge and reasoning skills across a diverse range of languages and cultural contexts.