TypeSafe Jev Played Chess — And Landed Next to Reasoning Models

Automated excerpt

I put Jev on LLM Chess anyway — same harness, same opponents as the chat models. With most chat models, stronger Dragon usually means fewer draws — the engine finishes more games. Jev has no chat, costs fractions of a cent per game, and still lands near mid-pack reasoning models on Elo.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.