theblackcat102/Qwen3-1.7B-Usefulness-Judge

The theblackcat102/Qwen3-1.7B-Usefulness-Judge is a 2 billion parameter Qwen3-based model developed by theblackcat102, specifically designed to evaluate the usefulness of a response to a given question. This model excels at determining if a response directly answers a question or avoids it, achieving an F1 score of 0.8248 in reasoning mode and 0.7681 in direct answer mode. It is optimized for automated content moderation and quality assurance tasks where response relevance is critical.