Model compare
Yingzao Fashi Assembly
Four live runs loaded side by side from the configured benchmark model set.
Missing runs for fable-5, composer-2-5, gpt-5-5, grok-4-5 on this benchmark.
Model compare
Four live runs loaded side by side from the configured benchmark model set.
Missing runs for fable-5, composer-2-5, gpt-5-5, grok-4-5 on this benchmark.