deepseek-ai

/

DeepSeek-R1

like 11.3k

Follow

DeepSeek 45.6k

EvalScope - LLM Evaluation Framework: https://github.com/modelscope/evalscope

1. Best Practices for Evaluating R1 Class Model Inference Capabilities
   https://evalscope.readthedocs.io/en/latest/best_practice/deepseek_r1_distill.html

2. Best Practices for Evaluating Reasoning Efficiency
   https://evalscope.readthedocs.io/en/latest/best_practice/think_eval.html

3. Best Practices for Evaluating R1, QwQ Inference Efficiency and Math-level:
   https://evalscope.readthedocs.io/en/latest/best_practice/eval_qwq.html