text_content.py

HEAD_TEXT = """
Based on the CRUXEVAL-X benchmark, we evaluated the executing and reasoning ability of different LLMs in 19 different programing languages.
            
More details about how to evalute the LLM are available in the [CRUXEVAL-X GitHub repository](https://github.com/CRUXEVAL-X/cruxeval-x). For a complete description of CRUXEVAL-X benchmark and related experimental analysis, please refer to the paper: [CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution](https://arxiv.org/abs/2408.13001). [![](https://img.shields.io/badge/arXiv-2408.13001-b31b1b.svg)](https://arxiv.org/abs/2408.13001)
**_Latest News_** 🔥
- [24/08/26] We release our CRUXEVAL-X benchmark, leaderboard and paper.
"""

ABOUT_TEXT = """# What is CRUXEVAL-X benchmark?
CRUXEVAL-X is a multilingual code reasoning, understanding and execution benchmark that focuses on code reasoning ability in different languages. 
Its goal is to evaluate LLM's code reasoning (given input, reasoning output; and given output, reasoning input) ability. 
# How to evaluate?
To facilitate evaluation on the CRUXEVAL-X benchmark, we provide the evaluation data and easy-to-use evaluation scripts in our [CRUXEVAL-X GitHub repository](https://github.com/CRUXEVAL-X/cruxeval-x). 
Additionally, factors involving execution-based evaluation are conducted in a virtual environment to ensure evaluation security.
# Contact
If you have any questions, feel free to reach out to us at [[email protected]](mailto:[email protected]).
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"

CITATION_BUTTON_TEXT = r"""@misc{xu2024cruxevalxbenchmarkmultilingualcode,
      title={CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution}, 
      author={Ruiyang Xu and Jialun Cao and Yaojie Lu and Hongyu Lin and Xianpei Han and Ben He and Shing-Chi Cheung and Le Sun},
      year={2024},
      eprint={2408.13001},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2408.13001}, 
}
"""

ACKNOWLEDGEMENT_TEXT = """
Inspired from the [🤗 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
"""


NOTES_TEXT = """
**Notes:**
- Evaluate using pass@1 as the evaluation metric.
- `Size` here is the amount of activated model weight during inference.
- `Average` denotes the average results of 19 different languages in a specific task.
- you can choose differt tasks in `⏬ Tasks`, `input reasoning` denotes given output, reasoning input, `output reasoning` denotes given input, reasoning output.
- `⏬ Languages` can choose languages you want to show in the leaderboard.
- For more explanation check the 📝 About section.
"""