Preparing Neural Aggregator
Streaming the page shell before the model grid is mounted.
Streaming the page shell before the model grid is mounted.
NNZen is a comparison explorer. It combines data from multiple sources and preserves source semantics instead of collapsing everything into a single “score”.
/api/v1/models/all (pricing, context length, capabilities/parameters, provider-specific information).A single model row can therefore mix sources: IDs and pricing may come from OpenRouter, ranks and category scores come from Arena, and old Arena-only rows may receive reviewed LiteLLM overlay metadata. The merged row is a projection with provenance, not a claim that one upstream source owns every field.
The production strategy is conservative: OpenRouter remains runtime truth, Arena remains evaluation truth, and LiteLLM is metadata overlay enrichment. Plain aliases are allowed only for reviewed identity matches. Search, grounding, high, thinking, and harness labels are stored as Arena eval profiles rather than collapsed into runtime model IDs.
Human-preference leaderboard signal. Useful for relative model performance in Arena categories, but still constrained by source coverage and availability.
Arena rank is not a universal product score. A model can be ranked in one category, absent in another, and missing entirely from one snapshot while still being strong in practice. OpenRouter columns are shown as raw metadata from /api/v1/models/all. No usage/popularity ranking is applied here.
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.
source_timestamps and source_health so clients can see which source is fresh and which one is lagging.snapshot_version identifies the current merged snapshot, while last_successful_snapshot is the last known-good merge recorded by the backend.using_last_good_snapshot is true, the UI is intentionally serving the last healthy merged snapshot because the newest primary merge is unavailable.last_merge_diff is a change summary, not a quality score. It tells you how many rows changed between merged snapshots, not whether the newer snapshot is “better”.source_timestamps first. If Arena is older than OpenRouter, mixed freshness is expected.using_last_good_snapshot is true before assuming the newest merge already shipped.arena_model_id_missing_reason before treating the row as a parser bug.Want to verify raw data? Use the public API endpoint /api/v1/models/all, then compare source timestamps and snapshot version with the UI summaries shown here.
Looking for model-specific details? Open any model page from the explorer for server-rendered identifiers, pricing, and source semantics.