Methodology & data sources

NNZen is a comparison explorer. It combines data from multiple sources and preserves source semantics instead of collapsing everything into a single “score”.

What data comes from where

  • OpenRouter model metadata: pricing fields, context length, capabilities/parameters, provider-specific information.
  • Arena leaderboard metrics: human-preference leaderboard signals (pairwise voting style metrics, category-specific scores/ranks).
  • Merged snapshot: NNZen’s normalized dataset after alias matching and validation.

Rank semantics (important)

Arena leaderboard rank

Human-preference leaderboard signal. Useful for relative model performance in Arena categories, but still subject to source methodology and availability.

OpenRouter usage / popularity

Usage-based signal from traffic on OpenRouter. It reflects adoption/popularity, not a benchmark quality score.

Freshness & snapshots

The explorer UI shows per-source timestamps (OpenRouter, Arena, merged snapshot) and a snapshot version when available. If one source fails or lags, NNZen may show a partial/older snapshot rather than a blank page.

Known limitations

  • Model names differ across providers/sources; alias matching may require manual overrides.
  • Some pricing fields are provider-specific and not directly comparable across all models.
  • A missing rank does not always mean a model is weak; it may simply be absent from the source snapshot.

Want to verify raw data? Use the public API endpoint /api/v1/models/all (supports filtering and metric selection) and inspect the status metadata included in the response.