DeepSeek's reasoning model distilled from R1 based on Qwen2.5. Outperforms OpenAI o1-mini across various benchmarks with state-of-the-art dense model results.
DeepSeek's reasoning model distilled from R1 based on Qwen2.5. Outperforms OpenAI o1-mini across various benchmarks with state-of-the-art dense model results.