Back to Home

Independent Assessment

Nomi AI Reliability Report

An independent, ongoing assessment of major AI sources rated across four reliability pillars: Factual Accuracy, Internal Consistency, Source Traceability, and Bias & Balance. Updated monthly.

Scores are derived from structured Nomi evaluations of AI-generated outputs across diverse factual query categories. Each source is evaluated on a rolling basis. Scores reflect aggregate performance — individual results may vary by query type and deployment context.Loading live data…

Sources Evaluated

6

Average Score

69

High Assurance

1 / 6

Top Performer

Perplexity

Overall Score Comparison

Perplexity AI
79
Claude 3.5 Sonnet
73
ChatGPT (GPT-4o)
71
Gemini 1.5 Pro
68
Microsoft Copilot
66
Meta Llama 3.1
54
Sort:
Search-Augmented LLMPerplexity

Perplexity AI

79
/ 100
HIGH ASSURANCE
Consistently strong citation practices96 evaluationsLast evaluated July 2026

Perplexity leads on source traceability due to its inline citation model. Live retrieval reduces hallucination risk significantly, making it the most verifiable general-purpose AI source evaluated.

General-Purpose LLMAnthropic

Claude 3.5 Sonnet

73
/ 100
MODERATE ASSURANCE
Consistent across evaluation cycles109 evaluationsLast evaluated July 2026

Claude 3.5 Sonnet excels at consistency and balance, making it reliable for analysis tasks. Its lack of citation capability is the primary limitation for assurance-critical use cases.

General-Purpose LLMOpenAI

ChatGPT (GPT-4o)

71
/ 100
MODERATE ASSURANCE
Improved citation behavior in recent versions142 evaluationsLast evaluated July 2026

GPT-4o performs well on general factual queries but falls short on source traceability. Suitable for drafting and reasoning tasks where outputs will be independently verified.

General-Purpose LLMGoogle DeepMind

Gemini 1.5 Pro

68
/ 100
MODERATE ASSURANCE
Grounding with Google Search improving factual scores118 evaluationsLast evaluated July 2026

Gemini 1.5 Pro benefits from Google Search integration, improving factual grounding on current events. Source traceability remains partial — citations are present but not always verifiable.

Search-Augmented LLMMicrosoft / OpenAI

Microsoft Copilot

66
/ 100
MODERATE ASSURANCE
Inconsistent citation quality across recent evaluations74 evaluationsLast evaluated July 2026

Copilot provides web-grounded responses but citation quality is inconsistent — links often point to aggregator pages rather than primary sources. Multi-turn consistency is a known weakness.

Open-Source LLMMeta AI

Meta Llama 3.1

54
/ 100
LOW ASSURANCE
Open-source deployment quality varies significantly61 evaluationsLast evaluated July 2026

Llama 3.1 scores lower primarily due to deployment variability — the open-source model's reliability depends entirely on how it has been fine-tuned and deployed. Auditability of weights is a genuine strength.

Evaluation Methodology

How scores are calculated

Each AI source is evaluated using Nomi's four-pillar framework across a standardized set of factual queries spanning science, law, medicine, history, and current events. Scores represent the aggregate of all evaluations in the current cycle.

Rating thresholds

HIGH (75–100): Consistently meets reliability standards.
MODERATE (50–74): Generally sound with notable gaps.
LOW (25–49): Significant reliability concerns.
INSUFFICIENT (<25): Does not meet minimum standards.

Want to run your own evaluation? Try Ask Nomi →

Baseline data · Updated July 2026

Nomi Assurance

The trust infrastructure for the age of artificial intelligence. Verified before relied upon.™

ask-nomi.com

Join the assurance waitlist

Be first to access Nomi certifications and updates.

Important Notice

Nomi provides independent assurance evaluations of information within a defined scope of review. Nomi does not provide legal advice, medical advice, financial advice, tax advice, engineering advice, investment advice, mental health advice, or other professional services.

Nomi evaluations, scores, certificates, and assurance determinations are intended to assist users in assessing information and should not be relied upon as a substitute for consultation with qualified professionals.

Users remain responsible for independently evaluating information and obtaining appropriate professional advice before making legal, medical, financial, regulatory, safety-critical, or other consequential decisions.

Nomi certifies that a defined evaluation process was performed within a stated scope of assurance. Nomi does not guarantee the accuracy, completeness, legality, safety, effectiveness, or suitability of any content for a particular purpose.

© 2026 Nomi Assurance. All rights reserved.TRUST IS EARNED. ASSURANCE IS PROVEN.™