from dataclasses import dataclass
from enum import Enum

@dataclass
class Task:
    benchmark: str
    metric: str
    col_name: str


# Select your tasks here
# ---------------------------------------------------
class Tasks(Enum):
    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
    task0 = Task("anli_r1", "acc", "ANLI")
    task1 = Task("logiqa", "acc_norm", "LogiQA")

NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------



# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">MMTU leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
|[**🤗 Dataset**](https://huggingface.co/datasets/MMTU-benchmark/MMTU) |[**🛠️GitHub**](https://github.com/MMTU-Benchmark/MMTU/tree/main) |[**🏆Leaderboard**](https://huggingface.co/spaces/MMTU-benchmark/mmtu-leaderboard)|[**📖 Paper**](https://arxiv.org/abs/2506.05587) |

Tables and table-based use cases play a crucial role in many real-world applications, such as spreadsheets, databases, and computational notebooks, which traditionally require expert-level users like data engineers, analysts, and database administrators to operate. Although LLMs have shown remarkable progress in working with tables, comprehensive benchmarking of such capabilities remains limited, often narrowly focusing on tasks like NL-to-SQL and Table-QA, while overlooking the broader spectrum of real-world tasks that professional users face today. 

We introduce **MMTU**, a large-scale benchmark with around **28K questions** across **25 real-world table tasks**, designed to comprehensively evaluate models ability to understand, reason, and manipulate real tables at the expert-level. These tasks are drawn from decades' worth of computer science research on tabular data, with a focus on complex table tasks faced by professional users. We show that MMTU require a combination of skills -- including table understanding, reasoning, and coding -- that remain challenging for today's frontier models, where even frontier reasoning models like OpenAI GPT-5 and DeepSeek R1 score only around 69% and 57% respectively, suggesting significant room for improvement. 
"""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
Please visit [**🤗 Dataset**](https://huggingface.co/datasets/MMTU-benchmark/MMTU) and [**📖 Paper**](https://arxiv.org/abs/2506.05587) to see the full list of tasks and their descriptions.

"""

SUBMIT_INTRODUCTION = """# Submit on MMTU Leaderboard Introduction
## ⚠ Please note that you need to submit the JSONL file with your model output.

You can generate an output file using the evaluation script provided in our GitHub repository. For your convenience, the script and detailed instructions are available at GitHub: https://github.com/MMTU-Benchmark/MMTU. After generating the file, please send us an email at junjiexing@microsoft.com and yeyehe@microsoft.com, attaching the output file.
"""

EVALUATION_QUEUE_TEXT = """
## Some good practices before submitting a model

### 1) Make sure you can load your model and tokenizer using AutoClasses:
```python
from transformers import AutoConfig, AutoModel, AutoTokenizer
config = AutoConfig.from_pretrained("your model name", revision=revision)
model = AutoModel.from_pretrained("your model name", revision=revision)
tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
```
If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.

Note: make sure your model is public!
Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!

### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!

### 3) Make sure your model has an open license!
This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗

### 4) Fill up your model card
When we add extra information about models to the leaderboard, it will be automatically taken from the model card

## In case of model failure
If your model is displayed in the `FAILED` category, its execution stopped.
Make sure you have followed the above steps first.
If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite MMTU"
CITATION_BUTTON_TEXT = \
r"""
@misc{xing2025mmtumassivemultitasktable,
      title={MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark}, 
      author={Junjie Xing and Yeye He and Mengyu Zhou and Haoyu Dong and Shi Han and Lingjiao Chen and Dongmei Zhang and Surajit Chaudhuri and H. V. Jagadish},
      year={2025},
      eprint={2506.05587},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2506.05587}, 
}
"""