# Curated leaderboard priors, keyed by model FAMILY (models.base_model_id).
#
# Why this file is hand-maintained rather than scraped: there is no unified
# leaderboard API, model naming differs everywhere (this catalog's `kimi-k3`
# against a leaderboard's "Kimi K3 (0731)"), and a scraper that silently
# starts returning nothing looks identical to a model that scores nothing.
#
# What it is FOR: cold start. NeuralWatt adds models, and a newly listed one
# has zero self-eval history — without a prior it sits at the neutral 0.5 and
# is indistinguishable from a model that was measured and found average. A
# prior gives it a defensible starting position until the eval harness has
# run enough samples to take over (proficiency.self_eval_min_samples).
#
# SHIPPED EMPTY ON PURPOSE. Inventing plausible-looking numbers here would put
# fabricated data directly into routing decisions — the same failure as the
# provider's static_fallback carbon constant, which this project already
# excludes for exactly that reason. Fill in only figures you actually looked
# up, and say where they came from in `source`.
#
# Serving variants inherit from their family automatically: an entry for
# `kimi-k3` covers kimi-k3-fast and kimi-k3-flex. Do not list variants.
#
# `python leaderboard.py` imports this and names any active family missing an
# entry. Categories must come from proficiency.categories in config.yaml, and
# scores are 0-1. Partial entries are fine — list only the categories a
# benchmark actually measures, and leave the rest to self-eval.

families: {}
  # Shape, for when you have real numbers to add:
  #
  # kimi-k3:
  #   source: "aider polyglot 2026-08-14; livebench 2026-08-01"
  #   scores:
  #     coding_general: 0.82
  #     coding_refactor: 0.79
  #     reasoning_math: 0.88
  #
  # gemma-4-31b:
  #   source: "lmarena 2026-08-10"
  #   scores:
  #     general_chat: 0.61