Skip to content
arXiv Board & Classic Game AI· Tidor-Vlad Pricope·· 24 d agoAI score34

RetroChessBench: A Benchmark for Reconstructing and Proving Chess Histories

RetroChessBench: A Benchmark for Reconstructing and Proving Chess Histories

AI summary

RetroChessBench is released, using 12 tasks to test whether models can reconstruct the legal move history of a chess game and distinguish events that could have occurred from events that must have occurred. Across two trials per task, GPT 6 Astra High failed to give the required final answer 22/24 times without tools and 18/24 times with code execution enabled, with average terminal RL rewards of 14.75% and 27.19%, respectively.

Source: arXiv Board & Classic Game AI · arxiv.org