Launching ChessArena – open-source Chess Benchmark to evaluate LLMs

Show HN: Launching ChessArena – open-source Chess Benchmark to evaluate LLMs

Based, Launching ChessArena – open-source Chess Benchmark to evaluate LLMs works in show hn launch.

Profile

A platform built to explore how large language models perform in chess games - OpenAI, Claude, Gemini.We created this platform using Motia to have a leaderboard of the best models in chess, but after researching and validating LLMs to play chess, we found that they can't really win games. This is because they don't have a good understanding of the game.In fact, the majority of the matches end in draws. So instead of tracking wins and losses, we focus on move quality and game insight. Each game is evaluated using Stockfish, the world's strongest open-source chess engine.How's it evaluated? On each move, we get what would be the best move using Stockfish to get the difference between the best

As a business in show hn launch, Launching ChessArena – open-source Chess Benchmark to evaluate LLMs is listed here with the public details available about it.

The company is listed at the Show HN launch stage of development.

Website: www.chessarena.ai