GitHub · by Maxim Saplin
LLM Chess: jev-latest
Jev played 80 games in a chess benchmark and made no illegal move.
Maxim Saplin’s benchmark plays models against a random opponent and scores them on wins, draws and rule-breaking. Jev’s published row is 80 games, 8 wins and 50 losses, zero wrong moves per 1,000, and about a tenth of a cent a game.
maxim-saplin/llm_chess on GitHub
- Stars
- 137
- Forks
- 15
- Language
- Python
- Last push
- Oct 14, 2026
Repository created Sep 28, 2024. Counts read from the GitHub API on Oct 15, 2026, and they move daily — quote them with the date.
