Language Models that Play Chess and Explain Their Moves

A 4B chess model that plays like a Grandmaster and explains its moves in plain English.

2697

Elo

Estimated playing strength after training

Beats every frontier LM tested, near median Grandmaster 2730

How it works

Experts can't explain
Chess engines play superhumanly but stay silent. Language models explain fluently but play weak moves, so their explanations mislead.
Bridge engine to LM
Cross-attention links the Lc0 chess encoder to SmolLM3-3B. A quiz curriculum teaches the bridge, then search-based explanations are repeatedly distilled back.
Strong play, solid prose
Elo rises from 1782 to 2697 over seven rounds. The model tops all baselines on puzzles and matches GPT-5.6-Sol on structural coherence.

From the paper