> ## Documentation Index
> Fetch the complete documentation index at: https://developers.agentx.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Model Comparison

> Per-model quality, cost, and latency aggregated from real traffic

Distinct from [Model portability](/evaluation/model-portability) (a what-if replay of one trace): Overview's **Model Comparison** card aggregates what your traffic already shows - every model observed in real traces over the window, with average judge rating, latency, token usage, and estimated cost side by side. No LLM calls involved, it's a pure read of data you already have; use it to notice that the cheaper model your team switched half the traffic to is also scoring a point lower.