Benchmark dataset for evaluating cross-lingual question answering performance

Factual and commonsense question benchmark dataset

Question and answer pair benchmark dataset

Mathematical reasoning benchmark dataset

Mathematical reasoning benchmark dataset

Mathematical reasoning benchmark dataset

A high quality dataset of user-assistant conversations generated by the OpenAssistant project.

Dataset of boolean expressions.

Human feedback, preference, and redteaming dataset from Anthropic. See https://arxiv.org/abs/2209.07858 and https://arxiv.org/abs/2204.05862

Test repo [test](https://www.oxen.ai/Laurence)