DeepSeek R1 Distill Qwen 14B is a distilled large language model based on Qwen 2.5 14B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
Other benchmark results include:
AIME 2024 pass@1: 69.7
MATH-500 pass@1: 93.9
CodeForces Rating: 1481
The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.
Recent activity on R1 Distill Qwen 14B
Total usage per day on OpenRouter
Prompt
7.39M
Reasoning
3.41M
Completion
1.43M
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.