Leveraging Reasoning Model Answers to Enhance Non-Reasoning Model Capability

A significant trend in enhancing the capabilities of these models is test-time scaling (Yang et al., 2025; Wu et al., 2025), where increasing computational resources allocated during inference leads to notable performance improvements. Models such as OpenAI's o1 series (OpenAI, 2024) and DeepSeek-R1 (DeepSeek-AI, 2025) have demonstrated the effectiveness of this approach across various tasks and benchmarks (Lightman et al., 2023; Huang et al., 2024). The capability of these models to achieve superior results by allocating additional computational resources during inference indicates an important shift in optimizing performance for LLMs. Specifically, dedicating more computation to the answer-generation process, rather than solely relying on scaling training data and model parameters, can lead to significant improvements, particularly in tasks that require complex reasoning (Snell et al., 2024). The success of test-time scaling thus emphasizes the crucial role of computation during the answer-generation phase.