Chinese ChessAI Capability Benchmark
A standardized benchmark evaluating frontier foundation models and specialized neural engines on discrete spatial reasoning and rules adherence. Featuring edge-native 10M Transformer.
LLM Xiangqi Benchmark
Rigorous sandbox and swap-opening pair evaluation assessing frontier models on spatial coherence, legal generation, and tactical solving.
Leaderboard OverviewEdge-Native Neural Model
Custom 9.74M Transformer with 32-ply action history attention. Verified past Pikafish UCI_Elo 2000 baseline with zero backend compute cost.
Explore Model ArchitecturePlay on Any Platform
Pure client-side WebAssembly execution with zero server inference cost. Offline native apps for macOS and Android.
Play in Browser NowPlay Online & Client Support
Experience discrete neural chess gameplay across multiple platforms
Zero installation required. Instant client-side inference powered by multithreaded ONNX Runtime Web.
Ergonomic mobile UI optimized for one-handed play with offline 10M neural model. Full standalone gameplay.
Native Compose Desktop application with hardware acceleration and configurable offline search depth.