GoBench - Track 1: leaderboard

Models play complete 9x9 Go games against a calibrated KataGo ladder through multi-turn APIs without tools. Each turn supplies the board, rules and legal moves; illegal outputs are retried. Elo ratings are fitted from game outcomes with a random-player anchor and color-advantage adjustment. Reasoning settings and dated model releases stay separate; the coding-engine and tutorial tracks are separate experiments.

Source: rolandgao.com.

Interactive version: theaggregate.ai/benchmark?slug=gobench-track-1 · How It Works · Data refreshed daily, snapshot 2026-10-25.