DeepSeek-R-1-7B

Emerging

2papers using it

2025first seen

The 'DeepSeek-R-1-7B' is a benchmark used to evaluate the reasoning accuracy and stability of large language models (LLMs) across general, coding, and STEM tasks.

🔎 Find this dataset

Papers using DeepSeek-R-1-7B (2)

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention2025

Compressing Chain-of-Thought in LLMs via Step Entropy2025

DeepSeek-R-1-7B dataset — papers, benchmarks & downloads · Large Language Models