How a new model joins the CompareLLM catalog
How a model enters the catalog: an explicit admin action, a draft hold, then the compare matrix grows.
Nothing is discovered automatically
An unmatched OpenRouter id becomes a Catalog candidate for an administrator to look at — it is never turned into a model. Creating the model is an explicit action, and it starts as a draft: not in the sitemap, not in compare pages. That stops one unverified marketplace listing from creating dozens of thin URLs overnight.
The row becomes publicly indexable only after an administrator confirms its identity and files evidence. Publication, tracking and search indexing are three separate decisions — a model can be published and still excluded from the rated boards, or served and deliberately not indexed.
What you do in /admin
File facts and evidence when you are ready, attach unmatched names as aliases, and approve only evidence that matches the exact model variant and version. Approve a news generation, edit the draft, then publish it separately. A public login cannot do any of this.
Ready to evaluate your stack?
Calculate your optimal model weights with Stack Engine or compare top models head-to-head.
Related guides
Same topic, next level of detail.
Explore More AI Intelligence Tools
Pairwise Model Comparisons
Compare any two models on our category ratings, speed classes and token pricing.
Curated 'Best-Of' Indexes
Targeted rankings for Best Coding LLMs, Best Cheap APIs, Shortest Wait, and top-tier models.
AI Hardware Calculator
Interactive VRAM calculator, quantization levels (FP16, Q8, Q4), KV cache context, and local hardware fit.
Live Market Intelligence
Live audit trail of benchmark updates, new model releases, and API price cuts.
Interactive Model Finder
Answer 5 quick questions to compute deterministic model recommendations for your use case.
Methodology & Standards
How a CompareLLM rating is computed, what evidence it admits, and how prices and speed classes are recorded.