← all datasets

Qwen-3-1.7B

Emerging
3papers using it
2025first seen

'Qwen-3-1.7B' is a benchmark used to evaluate the performance of models on reasoning tasks, specifically assessing their ability to optimize response quality and robustness through the application of the ADPO method.

🔎 Find this dataset

Papers using Qwen-3-1.7B (3)

Qwen-3-1.7B — datasets — reinforcement-learning