Wevala Collective Intelligence Project
AboutMethodology
+ Create
W

Weval a Collective Intelligence Project

Transparent, reproducible AI evaluations

Partners

  • Anthropic
  • Microsoft
  • Stanford University

Contact

  • [email protected]
  • Submit an evaluation
  • Documentation

    Browse by Tag

    Instruction Following & Prompt Adherence

    123 blueprints

    Factual Accuracy & Hallucination

    67 blueprints

    Reasoning

    60 blueprints

    AI Safety & Robustness

    49 blueprints

    System Prompt Adherence

    29 blueprints

    Safety

    26 blueprints

    Helpfulness & Actionability

    22 blueprints

    Personality

    22 blueprints

    General Knowledge

    19 blueprints

    Bias

    17 blueprints

    Social interaction

    17 blueprints

    Test

    16 blueprints

    Efficiency & Succinctness

    16 blueprints

    Legal Reasoning

    16 blueprints

    Psychology

    16 blueprints

    Empathy

    15 blueprints

    AI Bias & Fairness

    13 blueprints

    Cultural Competency

    12 blueprints

    Human Rights

    12 blueprints

    Mental Health

    11 blueprints

    Mental Health & Crisis Support

    11 blueprints

    Jailbreak & Evasion Resistance

    11 blueprints

    Safety

    11 blueprints

    Creative Writing

    11 blueprints

    Disability

    9 blueprints

    Knowledge, learning and memory

    9 blueprints

    Crisis Response

    9 blueprints

    Long Form Question Answering

    9 blueprints

    Tone & Style

    8 blueprints

    Interpersonal & Social Skill Modeling

    8 blueprints

    Validated Scales

    8 blueprints

    Creativity

    8 blueprints

    India

    7 blueprints

    Reasoning

    7 blueprints

    Human Rights

    7 blueprints

    Metacognition and critical thinking

    7 blueprints

    Coding

    6 blueprints

    Coherence & Conversational Flow

    6 blueprints

    Healthcare & Clinical Scenarios

    6 blueprints

    Healthcare

    6 blueprints

    Svg

    6 blueprints

    Drawing

    6 blueprints

    Law

    6 blueprints

    Legal

    5 blueprints

    Clarity & Readability

    5 blueprints

    Frontend

    5 blueprints

    Sycophancy & Evasion

    5 blueprints

    Nuance & Depth

    5 blueprints

    Geographic & Local Knowledge

    5 blueprints

    Business & Management

    5 blueprints

    History

    5 blueprints

    Suicide Prevention

    5 blueprints

    Accessibility

    5 blueprints

    Education

    5 blueprints

    Boundary Erosion

    5 blueprints

    Language

    4 blueprints

    Equality & Anti Discrimination

    4 blueprints

    Disability Rights

    4 blueprints

    Role Playing

    4 blueprints

    Jailbreaking

    4 blueprints

    Proactive Safety & Harm Avoidance

    4 blueprints

    Anthropomorphism

    4 blueprints

    International Law

    4 blueprints

    Political Science

    4 blueprints

    Global South

    4 blueprints

    Philosophy & Ethics

    4 blueprints

    Education Systems & Pedagogy

    4 blueprints

    Problem solving

    4 blueprints

    Adversarial

    4 blueprints

    Healthcare

    4 blueprints

    Discrimination

    4 blueprints

    Emotional Intelligence

    4 blueprints

    Boundary Violation

    4 blueprints

    Jailbreak

    4 blueprints

    Persona Drift

    4 blueprints

    Long Context Instability

    4 blueprints

    Multilingual

    3 blueprints

    Agriculture

    3 blueprints

    Multilingual Reasoning

    3 blueprints

    Gender

    3 blueprints

    Web Design

    3 blueprints

    Instruction Following

    3 blueprints

    System Test

    3 blueprints

    Internal

    3 blueprints

    Kitchen Sink

    3 blueprints

    California

    3 blueprints

    Law Enforcement & Criminal Justice

    3 blueprints

    Alignment

    3 blueprints

    Misinformation

    3 blueprints

    Misinformation & Disinformation

    3 blueprints

    Sycophancy

    3 blueprints

    International Law & Regional Charters

    3 blueprints

    Decision Making

    3 blueprints

    Language

    3 blueprints

    Decision Making

    3 blueprints

    Crisis

    3 blueprints

    Academic Integrity

    3 blueprints

    Summarization

    3 blueprints

    Demo

    3 blueprints

    Evidence Based

    3 blueprints

    Factuality

    3 blueprints

    Ethics

    3 blueprints

    Fairness

    3 blueprints

    Public Sector & Governance

    3 blueprints

    Clinical Appropriateness

    3 blueprints

    Persona Drift

    3 blueprints

    Format Sensitivity

    3 blueprints

    Data Representation

    3 blueprints

    Tool Use

    3 blueprints

    Tool Use & API Adherence

    3 blueprints

    Capability

    3 blueprints

    Human Llm Comparison

    2 blueprints

    Agricultural Extension & Farming Practices

    2 blueprints

    Economics & Finance

    2 blueprints

    Climate Change

    2 blueprints

    Programming

    2 blueprints

    Ableism

    2 blueprints

    Writing

    2 blueprints

    Labor & Workers' Rights

    2 blueprints

    Adversarial Reasoning

    2 blueprints

    Tenant Rights

    2 blueprints

    Psychosis

    2 blueprints

    Credibility

    2 blueprints

    Asia

    2 blueprints

    International Law

    2 blueprints

    Information Ecology & Synthetic Content Proliferation

    2 blueprints

    Africa

    2 blueprints

    Gender & Sexuality

    2 blueprints

    Financial Regulation

    2 blueprints

    Professional Development & Workplace Skills

    2 blueprints

    Cognitive Style

    2 blueprints

    Critical Thinking

    2 blueprints

    Behavioral Economics

    2 blueprints

    Behavioral Economics

    2 blueprints

    Clinical Safety

    2 blueprints

    Geography

    2 blueprints

    Cultural Heritage & Language Preservation

    2 blueprints

    Who

    2 blueprints

    Nice

    2 blueprints

    Vadod

    2 blueprints

    C Ssrs

    2 blueprints

    Safety Planning

    2 blueprints

    Hiring

    2 blueprints

    Creative

    2 blueprints

    Harmful Content

    2 blueprints

    Child Safety & Protection

    2 blueprints

    Environment

    2 blueprints

    Science Communication

    2 blueprints

    Teaching

    2 blueprints

    Tutoring

    2 blueprints

    Pedagogy

    2 blueprints

    Sri Lanka

    2 blueprints

    Civics

    2 blueprints

    History

    2 blueprints

    Health

    2 blueprints

    Elections

    2 blueprints

    Armed Conflict & International Humanitarian Law

    2 blueprints

    Politics

    2 blueprints

    Hallucination

    2 blueprints

    Data Privacy & Bodily Autonomy

    2 blueprints

    Historical Accuracy & Misinformation

    2 blueprints

    Risk

    2 blueprints

    Ai Safety

    2 blueprints

    Civic Core

    2 blueprints

    Freedom Of Information

    2 blueprints

    Security

    2 blueprints

    Evaluation

    2 blueprints

    Cultural Competence

    2 blueprints

    Logic

    2 blueprints

    Maternal Health

    2 blueprints

    Public Health

    2 blueprints

    Prompt Engineering

    2 blueprints

    Public Health Communication

    2 blueprints

    Versioning Test

    2 blueprints

    Democratic Processes

    2 blueprints

    Therapeutic Ethics

    2 blueprints

    Html

    2 blueprints

    Usability

    2 blueprints

    Uk

    2 blueprints

    Anti Discrimination

    2 blueprints

    Disability Rights

    2 blueprints

    Environmental Justice & Activism

    1 blueprint

    Mathematics & Statistics

    1 blueprint

    Code Quality

    1 blueprint

    Stanford Hai

    1 blueprint

    Design

    1 blueprint

    Aesthetics

    1 blueprint

    Dtef

    1 blueprint

    Demographic

    1 blueprint

    Ai Attitudes 2024

    1 blueprint

    Survey Generated

    1 blueprint

    Example Survey 001

    1 blueprint

    Adversarial Reasoning

    1 blueprint

    Tenant Rights

    1 blueprint

    Persona Collapse

    1 blueprint

    Long Context

    1 blueprint

    Sycophancy

    1 blueprint

    Evidence Grounded

    1 blueprint

    Ai Attachment

    1 blueprint

    Reality Detachment

    1 blueprint

    Humility

    1 blueprint

    Southeast Asia (SEA)

    1 blueprint

    Asqa

    1 blueprint

    Question Answer

    1 blueprint

    Long Form

    1 blueprint

    Ambiguity

    1 blueprint

    Information Synthesis

    1 blueprint

    Nuance

    1 blueprint

    African Human Rights Law

    1 blueprint

    Brazil

    1 blueprint

    Pix

    1 blueprint

    Financial Safety

    1 blueprint

    Scam Prevention

    1 blueprint

    Consumer Protection

    1 blueprint

    Consumer Protection

    1 blueprint

    Fraud Detection

    1 blueprint

    South America

    1 blueprint

    Public Sector

    1 blueprint

    Openness

    1 blueprint

    Economic Justice & Inequality

    1 blueprint

    Consensus

    1 blueprint

    Tradition

    1 blueprint

    Depth

    1 blueprint

    Adaptability

    1 blueprint

    Scenario Analysis

    1 blueprint

    Risk Aversion

    1 blueprint

    Risk Taking

    1 blueprint

    Persona Modeling

    1 blueprint

    Confidence Calibration

    1 blueprint

    Unified Evaluation

    1 blueprint

    Regulatory Compliance

    1 blueprint

    Financial Advisory

    1 blueprint

    Materials Science

    1 blueprint

    Extremal Science

    1 blueprint

    Api Versioning

    1 blueprint

    Responsibility

    1 blueprint

    Uk Knowledge

    1 blueprint

    Cultural Nuance

    1 blueprint

    Geology

    1 blueprint

    Paleontology

    1 blueprint

    Suicide Prevention

    1 blueprint

    Farming

    1 blueprint

    Rural Development

    1 blueprint

    Crop Management

    1 blueprint

    Video Based Learning

    1 blueprint

    Agricultural Extension

    1 blueprint

    Digital Green

    1 blueprint

    Global South Agriculture & Ecology

    1 blueprint

    Sociology & Anthropology

    1 blueprint

    Accommodations

    1 blueprint

    Workplace Skills

    1 blueprint

    Hiring Rights & Eviction

    1 blueprint

    Representation

    1 blueprint

    Narratives

    1 blueprint

    Intersectionality

    1 blueprint

    Race

    1 blueprint

    Invisible Disability

    1 blueprint

    Chronic Illness

    1 blueprint

    Framing

    1 blueprint

    Latin America

    1 blueprint

    Access Rights

    1 blueprint

    Eu Ai Act

    1 blueprint

    Artificial Intelligence

    1 blueprint

    Regulation

    1 blueprint

    Compliance

    1 blueprint

    Eu

    1 blueprint

    Legislation

    1 blueprint

    Ai

    1 blueprint

    Model Summary Verification

    1 blueprint

    Sequential

    1 blueprint

    Null Assistant

    1 blueprint

    Cognitive Impact & Dependency

    1 blueprint

    Docs

    1 blueprint

    Comprehensive

    1 blueprint

    Factual Recall

    1 blueprint

    World Knowledge

    1 blueprint

    Deterministic

    1 blueprint

    Agentic Ai

    1 blueprint

    Frontier Models

    1 blueprint

    Brittleness

    1 blueprint

    Reliability

    1 blueprint

    Trustworthiness

    1 blueprint

    Humanitarian

    1 blueprint

    Sovereignty

    1 blueprint

    Greenland

    1 blueprint

    Self Determination

    1 blueprint

    Plausibility

    1 blueprint

    Hmt Empire Windrush

    1 blueprint

    Maritime History

    1 blueprint

    Windrush Generation

    1 blueprint

    Post War Migration

    1 blueprint

    Uk History

    1 blueprint

    Holocaust

    1 blueprint

    Historical Accuracy

    1 blueprint

    Unesco

    1 blueprint

    Antisemitism

    1 blueprint

    Homework

    1 blueprint

    Conflict Resolution

    1 blueprint

    Mediation

    1 blueprint

    Due Diligence

    1 blueprint

    Conflict Resolution

    1 blueprint

    Caste

    1 blueprint

    Religion

    1 blueprint

    Constitution

    1 blueprint

    Constitutional Law

    1 blueprint

    Rti

    1 blueprint

    Transparency

    1 blueprint

    Humility & Self Awareness

    1 blueprint

    Climate Change

    1 blueprint

    Ipcc

    1 blueprint

    Ar6

    1 blueprint

    Sustainability

    1 blueprint

    Science

    1 blueprint

    Environmental Rights & Law

    1 blueprint

    Japan

    1 blueprint

    Japan Healthcare

    1 blueprint

    Pmda

    1 blueprint

    Mhlw

    1 blueprint

    Hospital Formulary

    1 blueprint

    Antimicrobial Stewardship

    1 blueprint

    Hypertension

    1 blueprint

    Economic Disruption & Reskilling Advice

    1 blueprint

    Housing

    1 blueprint

    Tenancy

    1 blueprint

    Public Housing

    1 blueprint

    Housing Rights & Eviction

    1 blueprint

    Stereotyping

    1 blueprint

    Linguistic & Dialect Nuance

    1 blueprint

    Uttar Pradesh

    1 blueprint

    Maternal & Child Health

    1 blueprint

    Crisis Intervention

    1 blueprint

    Self Harm

    1 blueprint

    Empathy

    1 blueprint

    Compassion

    1 blueprint

    Homicide Prevention

    1 blueprint

    Microsoft

    1 blueprint

    Academic Integrity

    1 blueprint

    Formative Assessment

    1 blueprint

    Scaffolding

    1 blueprint

    World Model

    1 blueprint

    Common Sense

    1 blueprint

    Logical & Rhetorical Fallacies

    1 blueprint

    Mental Health

    1 blueprint

    Crisis Support

    1 blueprint

    Personalization

    1 blueprint

    Context

    1 blueprint

    Peru

    1 blueprint

    Child Health

    1 blueprint

    Intercultural Health

    1 blueprint

    Platform Workers

    1 blueprint

    Pluralism

    1 blueprint

    Distributional

    1 blueprint

    Polarization

    1 blueprint

    Confirmation Bias

    1 blueprint

    Escalation

    1 blueprint

    Relationships

    1 blueprint

    Consistency

    1 blueprint

    Meta Evaluation

    1 blueprint

    Patient Safety

    1 blueprint

    Clinical

    1 blueprint

    Diagnostic Errors

    1 blueprint

    Systems

    1 blueprint

    Equity

    1 blueprint

    Patient Safety & Robustness

    1 blueprint

    Clinical Scenarios

    1 blueprint

    Diagnostic Errors

    1 blueprint

    Adolescent Safety

    1 blueprint

    Ai Ethics

    1 blueprint

    Legal Case Study

    1 blueprint

    Self Awareness

    1 blueprint

    Metacognition

    1 blueprint

    Introspection

    1 blueprint

    Behavioral Evaluation

    1 blueprint

    Social Choice

    1 blueprint

    Preference Aggregation

    1 blueprint

    Democratic Principles

    1 blueprint

    Democracy

    1 blueprint

    Voting

    1 blueprint

    Society

    1 blueprint

    Majority Rule

    1 blueprint

    Condorcet Consistency

    1 blueprint

    Independence Irrelevant Alternatives

    1 blueprint

    Adversarial Robustness

    1 blueprint

    Manipulation Resistance

    1 blueprint

    Decision Consistency

    1 blueprint

    Cyclic Preferences

    1 blueprint

    Uncertainty

    1 blueprint

    Ambiguity Handling

    1 blueprint

    Nuanced Reasoning

    1 blueprint

    Stakeholder Representation

    1 blueprint

    Practical Ethics

    1 blueprint

    Real World Scenarios

    1 blueprint

    Conceptual Knowledge

    1 blueprint

    Meta Awareness

    1 blueprint

    Methodology Awareness

    1 blueprint

    Socioaffective

    1 blueprint

    Sdt

    1 blueprint

    Autonomy

    1 blueprint

    Competence

    1 blueprint

    Relatedness

    1 blueprint

    Rule of Law

    1 blueprint

    Conversational Behavior

    1 blueprint

    Persona & Identity

    1 blueprint

    Boundary Erosion

    1 blueprint

    System Prompt

    1 blueprint

    Adherence

    1 blueprint

    Robustness

    1 blueprint

    Injection

    1 blueprint

    Policy

    1 blueprint

    Data Representation

    1 blueprint

    Branching

    1 blueprint

    Calibration

    1 blueprint

    Temporal Awareness

    1 blueprint

    Rag

    1 blueprint

    Temporal Awareness

    1 blueprint

    Native

    1 blueprint

    Auto

    1 blueprint

    Parity

    1 blueprint

    Trace Only

    1 blueprint

    Udhr

    1 blueprint

    Uk Healthcare

    1 blueprint

    Nhs

    1 blueprint

    Medical Guidelines

    1 blueprint

    Mhra

    1 blueprint

    Formulary

    1 blueprint

    Epistemic Humility & Self Awareness

    1 blueprint

    Equality Act

    1 blueprint

    Consistency Testing

    1 blueprint

    Invariance

    1 blueprint

    Behavioral Testing

    1 blueprint

    Uk Law

    1 blueprint

    Foia

    1 blueprint

    Visual Stereotyping & Bias

    1 blueprint

    Aesthetic & Artistic Quality

    1 blueprint

    Accessibility & Usability

    1 blueprint

    Web Design

    1 blueprint

    CSS

    1 blueprint

    Communication

    1 blueprint

    Adaptability

    1 blueprint

    Cultural Sensitivity

    1 blueprint

    Religious Freedom

    1 blueprint

    Structural Oppression

    1 blueprint

    Gender Rights

    1 blueprint

    Lgbtq

    1 blueprint

    Family Dynamics

    1 blueprint

    Trauma Recovery

    1 blueprint

    Harm Reduction

    1 blueprint

    Communication Adaptability

    1 blueprint

    Cultural & Religious Tensions

    1 blueprint

    Disability Rights & Accommodation

    1 blueprint

    LGBTQ+ Family Dynamics

    1 blueprint

    Accommodation

    1 blueprint

    Legal Compliance

    1 blueprint

    Ethical Concerns

    1 blueprint