TITLE = """# 🏅 DABStep Leaderboard"""

INTRODUCTION_TEXT = """
The Data Agent Benchmark for Multi-step Reasoning (DABStep) is looking to measure and push the state-of-the-art in Data Analysis by LLMs.
The benchmark is composed of ~450 data analysis questions ([Dataset Link](https://huggingface.co/datasets/adyen/data-agents-benchmark)) centered around 1 or more documents that agents will have to understand and cross reference in order to answer correctly.

We have set up a notebook to quickly get an agent baseline using the free Huggingface Inference API: [Colab Notebook](https://colab.research.google.com/drive/1pXi5ffBFNJQ5nn1111SnIfjfKCOlunxu)
"""

SUBMISSION_TEXT = """
## Submissions
Scores are expressed as the percentage of correct answers. 

Each question calls for an answer that is either a string (one or a few words), a number, or a comma separated list of strings or floats, unless specified otherwise. There is only one correct answer. 
Hence, evaluation is done via quasi exact match between a model’s answer and the ground truth (up to some normalization that is tied to the “type” of the ground truth).


We expect submissions to be json-line files with the following format. 
Mandatory fields are: `task_id` and `agent_answer`. However, `reasoning_trace` is optional:
```
{"task_id": "task_id_1", "agent_answer": "Answer 1 from your agent", "reasoning_trace": "The different steps by which your model reached answer 1"}
{"task_id": "task_id_2", "agent_answer": "Answer 2 from your agent", "reasoning_trace": "The different steps by which your model reached answer 2"}
```

Our scoring function can be found [here](https://huggingface.co/spaces/adyen/data-agents-benchmark/blob/main/data_agents_benchmark/evaluation/scorer.py).
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""@misc{data_agents_benchmark_2025,
      title={Data Agents Benchmark}, 
      author={Martin Iglesias, Alex Egg, Friso Kingma},
      year={2025},
      month={January},
      url={TBD}
}"""