Word ladder (shortest path)

llama3.2-3b

Pythononeshotrun 2sample 08.7s wall

← run 2 · raw JSON · challenge definitions

100

score

tests (60%)5/5 passed

deliverables (20%)100%

content checks (20%)100%

01 what the model was asked

Create ladder.py with exactly one function:

ladder_length(begin: str, end: str, word_list: list[str]) -> int
    A transformation sequence goes from begin to end, changing exactly one letter per step; every intermediate word (and end itself) must appear in word_list. Return the number of words in the SHORTEST such sequence counting both endpoints, or 0 if none exists. begin does not need to be in word_list. All words are lowercase and the same length.

Example: begin="hit", end="cog", word_list=["hot","dot","dog","lot","log","cog"] -> 5 (hit -> hot -> dot -> dog -> cog).

Use only the Python standard library. A breadth-first search is the intended approach; brute-force recursion will be too slow for the larger test.

required deliverables + checks

✓deliverable: ladder.py

✓ladder.py must contain “def ladder_length”

pytest suite it was graded against

test_ladder.py · 27 lines · 744 B

import time from ladder import ladder_length  def test_classic_example():    assert ladder_length("hit", "cog", ["hot", "dot", "dog", "lot", "log", "cog"]) == 5  def test_unreachable_end():    assert ladder_length("hit", "cog", ["hot", "dot", "dog", "lot", "log"]) == 0  def test_single_step():    assert ladder_length("a", "c", ["a", "b", "c"]) == 2  def test_shortest_is_found():    words = ["hot", "hit", "hat", "cat", "cot", "cog", "dog"]    assert ladder_length("hit", "cot", words) == 3  def test_larger_input_is_fast():    words = [a + b + c for a in "abcdefgh" for b in "abcdefgh" for c in "abcdefgh"]    start = time.monotonic()    assert ladder_length("aaa", "hhh", words) == 4    assert time.monotonic() - start < 2.0

02 what it did — full transcript

promptthe exact instruction sent to the model

view full prompt

You are completing a coding task in one shot. Write complete files that satisfy the spec below. Tests (pytest) will be run against your files; you cannot run them yourself.

Reply with ONE JSON object and nothing else:
{"files": {"<relative path>": "<complete file content>", ...}}

Required deliverable files: ladder.py

SPEC:
Create ladder.py with exactly one function:

ladder_length(begin: str, end: str, word_list: list[str]) -> int
    A transformation sequence goes from begin to end, changing exactly one letter per step; every intermediate word (and end itself) must appear in word_list. Return the number of words in the SHORTEST such sequence counting both endpoints, or 0 if none exists. begin does not need to be in word_list. All words are lowercase and the same length.

Example: begin="hit", end="cog", word_list=["hot","dot","dog","lot","log","cog"] -> 5 (hit -> hot -> dot -> dog -> cog).

Use only the Python standard library. A breadth-first search is the intended approach; brute-force recursion will be too slow for the larger test.

reply196 tokens

view raw reply

{"files": {"ladder.py": "import collections\nfrom typing import List\n\ndef ladder_length(begin: str, end: str, word_list: List[str]) -> int:\n    if begin not in word_list and end not in word_list:\n        return 0\n    word_set = set(word_list)\n    queue = [(begin, 1)]\n    visited = {begin}\n    while queue:\n        word, step = queue.pop(0)\n        for i in range(len(word)):\n            for char in 'abcdefghijklmnopqrstuvwxyz':\n                new_word = word[:i] + char + word[i+1:] \n                if new_word not in visited and new_word in word_set:\n                    if new_word == end:\n                        return step + 1\n                    queue.append((new_word, step + 1))\n                    visited.add(new_word)\n    return 0"}}

write_fileladder.py · 719 B

graded 100.05 passed, 0 failed

pytest output

.....                                                                    [100%]
5 passed in 0.01s

03 what it wrote

files

lines

source lines

functions

classes

cyclomatic

max nesting

17.0

avg fn lines

stdlib imports: collections, typing

File	LOC	SLOC	Fns	Complexity	Depth	Imports
ladder.py	20	19	1	9	6	collections, typing

ladder.py · 20 lines · 719 B

import collectionsfrom typing import List def ladder_length(begin: str, end: str, word_list: List[str]) -> int:    if begin not in word_list and end not in word_list:        return 0    word_set = set(word_list)    queue = [(begin, 1)]    visited = {begin}    while queue:        word, step = queue.pop(0)        for i in range(len(word)):            for char in 'abcdefghijklmnopqrstuvwxyz':                new_word = word[:i] + char + word[i+1:]                 if new_word not in visited and new_word in word_set:                    if new_word == end:                        return step + 1                    queue.append((new_word, step + 1))                    visited.add(new_word)    return 0

04 how it was graded

✓ ok 5/5 passed

model calls

invalid actions

self test runs

196

tokens out

—

tokens in

8.7s

wall time

agent actions: —

final pytest output

.....                                                                    [100%]
5 passed in 0.01s