docs(evaluate): Models page — configuring models for evaluation

[sephmard]

Part of #1436 — Evaluate section restructure.

There is currently no dedicated page explaining how to configure models specifically for evaluation runs — model choice, sampling settings, repeat counts, and how these affect score reliability.

Tasks

• Create fern/versions/latest/pages/evaluation/models.mdx
• Cover:
  • Choosing a model for evaluation (policy model, reference model)
  • Relevant config fields (model_name, sampling_params, repeat count)
  • How sampling settings interact with pass@1 vs pass@k
  • Linking to Configure Models for server-level setup
• Add navigation card in evaluation index
• fern check passes