Artificial Analysis Openness Index
Openness Index
Openness Index
Openness Index
Artificial Analysis Openness Index: Score
Index Components
Artificial Analysis Openness Index: Components
Transparency vs. Availability
Artificial Analysis Openness Index: Model Availability vs. Model Transparency
Openness Index vs. Release Date
Artificial Analysis Openness Index: Score vs. Release Date
Openness vs. Intelligence
Artificial Analysis Openness Index vs. Artificial Analysis Intelligence Index
Openness Index Composition
Scoring methodology
Each component is scored on a 0-3 qualitative scale based on the best-fitting openness 'archetype', with each model assessed based on the full set of public first-party information available.
We synthesize these underlying factors into a unified metric, the Artificial Analysis Openness Index, as follows:
- Data elements are averaged between pre- and post-training (to give a total of 6 possible points across data)
- All component scores are added (up to a maximum of 18/18 points)
- This score is normalized to a 0-100 scale
Where models are derived from a third-party base model, they may be constrained by the licensing or limited disclosure of the upstream model. For incremental/update releases, we only consider disclosures explicitly about the new release (including allowing model creators to declare which components remain consistent with an earlier release).
Openness Index Leaderboard
Creator | Model | Openness Index | Intelligence Index | Model Availability | Model Transparency | Pre-training Data Access | Pre-training Data License | Post-training Data Access | Post-training Data License | |
|---|---|---|---|---|---|---|---|---|---|---|
| 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 |
Frequently Asked Questions
The Artificial Analysis Openness Index is a composite score that measures how openly available and transparently documented AI models are, including model weights, licensing, training data, training methodology, and training code.
The Artificial Analysis Openness Index scores models on a qualitative 0 to 3 scale across model availability (weights access and license) and model transparency (training data access and license, methodology disclosure, and training pipeline release). Data scores are averaged between pre- and post-training, and the component scores are summed to a maximum of 18, then normalized to a 0 to 100 scale.
K2 Think V2 currently has the highest Artificial Analysis Openness Index score, with a score of 89 among models with published Openness Index results. View model
Open and transparent models support reproducibility, independent evaluation, customization for specific use cases, and commercial use without lock-in. The Artificial Analysis Openness Index gives a single comparable score for how open a model is, so users can weigh openness alongside intelligence, speed, and price when choosing a model.
No. Open weights means the model weights are available, but it does not guarantee that source code, training data, training recipes, or permissive licenses are available. The Artificial Analysis Openness Index scores these factors separately to distinguish models that are accessible from models that are broadly open and transparent.
Explore Evaluations
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.
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.
CritPt v2 BenchmarkCritPt v2 is the revised version of CritPt, a benchmark designed to test LLMs on research-level physics reasoning tasks, featuring 70 composite research challenges. Models solve problems with a code-execution tool in an offline Linux sandbox.
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.
CritPt BenchmarkA benchmark designed to test LLMs on research-level physics reasoning tasks, featuring 71 composite research challenges.
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.