Top Model List — LLM head-to-head comparison

Data-driven comparison of frontier LLMs: benchmark leaderboards (Coding / Agentic / Reasoning / Vision / Long Context), per-token API pricing, and subscription plans. Every score links to its evidence source. This site needs JavaScript for the interactive views; the underlying data is available as machine-readable YAML:

models.yaml — 35 models with pricing & context windows
benchmarks.yaml — 49 benchmark definitions & sources
scores.yaml — 358 model × benchmark scores with evidence
providers.yaml — vendor metadata
config.yaml — site configuration
llms.txt — site summary for AI agents
llms-full.txt — full markdown content for AI agents

Source repository