# Grain model leaderboard

> Independent results from Grain’s own benchmark harness on the models Grain runs: one ranked board per measured task set, with sample size, price per million tokens, and method. Shows a "first results coming" state until a campaign is published.

- Canonical page: [/leaderboard](https://grain.sh/leaderboard)
- Agent-readable page: [/agents/leaderboard.md](https://grain.sh/agents/leaderboard.md)
- Section: Benchmarks

## What this page covers

- Ranked boards per task set
- Sample size (n) on every score; early results below n=3
- Price in/out per million tokens from Grain’s catalog
- Overall ranking when two or more boards are measured
- Methodology

## About Grain

Grain is a multi-agent work platform. A person describes an outcome as a Mission, Grain coordinates the models, tools, files, repositories, and connected computers needed to do the work, and the result returns for review.

Start with [the complete agent-readable index](https://grain.sh/agents/index.md) or read [the full site corpus](https://grain.sh/llms-full.txt).