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">WebCoderBench</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
"""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = """
## About WebCoderBench

Web applications (web apps) have become a key arena for large language models (LLMs) to demonstrate code generation capabilities and commercial potential. However, building a benchmark for LLM-generated web apps remains challenging due to:

- The need for real-world user requirements
- Generalizable evaluation metrics without relying on ground-truth implementations or test cases
- Interpretable evaluation results

---

## What Is Included

WebCoderBench is a real-world-collected, generalizable, and interpretable benchmark for web app generation.

**At a glance**

- **1,572** real-world user requirements
- Diverse modalities and expression styles reflecting realistic user intentions
- **24** fine-grained evaluation metrics across **9** perspectives

---

## How It Is Evaluated

WebCoderBench combines **rule-based evaluation** and the **LLM-as-a-judge** paradigm to enable fully automated, objective, and general evaluation.

To make the overall ranking more interpretable, we adopt **human-preference-aligned weights** over metrics to yield overall scores.

---

## Key Findings

Experiments across **12 representative LLMs** and **2 LLM-based agents** show that there is **no dominant model across all evaluation metrics**, offering opportunities for targeted optimization.
"""

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 these results"
CITATION_BUTTON_TEXT = r"""
"""