"""Streamlit theme helpers for the GRM leaderboard.""" CUSTOM_CSS = """ """ LIGHT_THEME_CSS = """ """ DARK_THEME_CSS = """ """ def palette_css(light_mode: bool) -> str: return LIGHT_THEME_CSS if light_mode else DARK_THEME_CSS HEADER_HTML = """
NVIDIA Game Ready Evaluation

Game Ready Leaderboard

An open game model evaluation surface for comparing LLMs across roleplay, gameplay actions, and practical in-game reasoning.

""" OVERVIEW_BLOCKS = [ "Nvidia Game Ready Model Score (GRM) is an aggregated quality metric designed to assess LLM capabilities in gaming use cases.", "General state-of-the-art language models are optimized for broad benchmarks such as math, code, and general knowledge. That does not reliably translate to in-game performance, and it does not reliably predict NPC quality, gameplay actions, or immersion.", "With game model evaluation, game developers can accelerate AI integration pipelines by reducing time spent on model evaluation and narrowing model choice earlier. The overall score is the average of Roleplay, Actions, and General, while benchmarks inside each category are combined with weighted averaging using the PRD weights.", ] FORMULAS = [ "GRM Score = (Roleplay + Actions + General) / 3", "Category Score = sum(score x weight) / sum(weight)", ]