Llama 3.3 70B × binary-search

7.3

Algorithm + full docstring (Args/Returns/Raises + examples)

correctness 7.0quality 7.0documentation 8.01495ms

$ cat binary-search.prompt — what the model was asked

Implement `binary_search(arr: list[int], target: int) -> int` in Python. It should return the index of target in a sorted list, or -1 if not found. Write a proper docstring with Args, Returns, and Raises sections. Add inline comments explaining the algorithm logic. Include 3 test cases as examples in the docstring.

run 1 of 1

7.3

correctness 7.0quality 7.0documentation 8.01495ms

# judge: Core binary search logic is correct, but raising ValueError for empty list deviates from the spec's expectation of returning -1, and mid-calculation doesn't address overflow-safe alternative despite rubric interest; comments are somewhat redundant but docstring and examples are otherwise complete and accurate.

$ cat llama-3.3-70b.binary-search.r1.response

```python
def binary_search(arr: list[int], target: int) -> int:
    """
    This function performs a binary search on a sorted list to find the index of a target value.
    
    Args:
        arr (list[int]): A sorted list of integers.
        target (int): The target value to be searched in the list.
    
    Returns:
        int: The index of the target in the list if found, -1 otherwise.
    
    Raises:
        ValueError: If the input list is empty.
    
    Examples:
        >>> binary_search([1, 2, 3, 4, 5], 3)
        2
        >>> binary_search([1, 2, 3, 4, 5], 6)
        -1
        >>> binary_search([1, 2, 3, 4, 5], 1)
        0
    """
    
    # Check if the input list is empty
    if not arr:
        raise ValueError("Input list is empty")
    
    # Initialize two pointers, low and high, to the start and end of the list
    low = 0  # lowest index in the current search range
    high = len(arr) - 1  # highest index in the current search range
    
    # Continue the search until the search range is not empty
    while low <= high:  # if low is still less than or equal to high, the search range is not empty
        # Calculate the middle index of the current search range
        mid = (low + high) // 2  # integer division to get the middle index
        
        # If the target is found at the middle index, return the middle index
        if arr[mid] == target:
            return mid  # target found, return its index
        
        # If the target is less than the middle element, update the high pointer
        elif arr[mid] > target:
            high = mid - 1  # search in the left half of the current range
        
        # If the target is greater than the middle element, update the low pointer
        else:
            low = mid + 1  # search in the right half of the current range
    
    # If the target is not found after the search, return -1
    return -1  # target not found


# Test cases
print(binary_search([1, 2, 3, 4, 5], 3))  # Output: 2
print(binary_search([1, 2, 3, 4, 5], 6))  # Output: -1
print(binary_search([1, 2, 3, 4, 5], 1))  # Output: 0
```

To run this code, save it to a file (e.g., `binary_search.py`) and execute it using Python (e.g., `python binary_search.py`). The test cases are included at the end of the code. You can modify the test cases to test the function with different inputs.