← News / June 18, 2026 Transparency

How We Cite Sources in Our LLM Rankings

Full methodology: where our data comes from, how we verify it, when we update it, and why transparency is the foundation of every ranking we publish.

Every number on our LLM Models and Cost Comparison pages comes from a traceable source. We publish this methodology page for the same reason we require citation from the models we evaluate: accountability.

This page covers where we get our data, how we weight our rankings, how often we update, what we won't publish, and how you can verify our claims.

Our Data Sources — 4 Tiers

We use a four-tier sourcing hierarchy. Tier 1 is the most authoritative; Tier 4 is supplemental context only.

Tier 1 — Official Provider Documentation

Model developers publish their own benchmark results, pricing, and technical specifications. These are our primary sources for:

We treat provider-claimed benchmarks as the starting point, not the final word. When independent evaluations (Tier 2) disagree with provider claims by more than 5%, we flag the discrepancy and default to the independent score.

Tier 2 — Independent Evaluation Platforms

Third-party evaluators provide cross-model comparisons under standardized conditions. Our Tier 2 sources:

Tier 3 — Peer-Reviewed Research

We track academic papers that include model evaluations, particularly for:

When we cite a research paper, we link to it directly. If the paper is behind a paywall, we link to the preprint on arXiv or the author's institutional repository.

Tier 4 — Our Own API Testing

For metrics not covered by the above — particularly hallucination rates in long-context scenarios and real-world latency measurements — we run our own standardized test suites directly against each model's API. Our test methodology:

Ranking Methodology — How We Score

Our overall model rankings use a weighted composite of six factors:

Factor Weight Source
GPT Benchmark (composite) 30% Tier 1 (provider-claimed, verified)
MMLU Accuracy 20% Tier 1 + Tier 2 (HELM cross-check)
LMSys ELO Rating 20% Tier 2 (LMSys Chatbot Arena)
Context Window Size 10% Tier 1 (official specs)
Hallucination Rate 10% Tier 4 (our own testing) + TruthfulQA
Cost Efficiency (score/$) 10% Tier 1 (official pricing)

Each factor is normalized to a 0–100 scale. The weighted average produces the overall score. We publish the raw factor scores on our models page so readers can re-weight according to their own priorities — if cost matters more to you than context window, the data is there to recalculate.

Update Cadence

Data Type Update Frequency Trigger for Off-Cycle Update
Pricing Monthly Any provider price change >10%
Benchmark scores Quarterly New major benchmark release
Model roster Continuous New flagship model from any provider
Hallucination rates Quarterly Major model update or new safety findings
News articles As published N/A — each article has its own date

The "last updated" date is visible on every data page. If a page says "Updated June 2026," every number on that page was verified against its source in June 2026.

What We Don't Publish

Transparency also means being clear about what's not on our pages:

How to Verify Our Claims

We want readers to fact-check us. Here's how:

  1. Pricing: Follow the provider links in our cost comparison page — they go directly to official pricing pages.
  2. Benchmarks: Cross-reference our scores against LMSys Chatbot Arena and Stanford HELM.
  3. Hallucination rates: Our test methodology is described above. We encourage independent replication.
  4. Model specs: Compare against each provider's official model card. We link to them on our developer guide.

If you find an error, tell us. We publish corrections prominently and update the "last modified" date. Accuracy matters more than being right the first time.

Why This Page Exists

Google's EEAT guidelines (Experience, Expertise, Authoritativeness, Trustworthiness) reward sites that demonstrate transparency about their information sources. More importantly, trust is earned through verification, not claims. Every number on our ranking pages should be independently verifiable by a reader with an internet connection and a few minutes.

If you can't verify it, we haven't done our job.

Updated June 18, 2026. Methodology last reviewed June 2026. See the current rankings → or compare pricing →

← Back to News