Word ladder (shortest path)
qwen3-30b-a3b
Pythononeshotrun 2sample 0196.3s 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.
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.
reply4442 tokens
view raw reply
{"files": {"ladder.py": "from collections import deque\n\ndef ladder_length(begin: str, end: str, word_list: list[str]) -> int:\n word_set = set(word_list)\n if end not in word_set:\n return 0\n if begin == end:\n return 1\n queue = deque()\n queue.append((begin, 1))\n visited = set([begin])\n while queue:\n current, steps = queue.popleft()\n if current == end:\n return steps\n for i in range(len(current)):\n for c in 'abcdefghijklmnopqrstuvwxyz':\n new_word = current[:i] + c + current[i+1:]\n if new_word in word_set and new_word not in visited:\n visited.add(new_word)\n queue.append((new_word, steps + 1))\n return 0"}}write_fileladder.py · 727 B
graded 100.05 passed, 0 failed
pytest output
..... [100%] 5 passed in 0.02s
03 what it wrote
1
files
22
lines
21
source lines
1
functions
0
classes
9
cyclomatic
5
max nesting
20.0
avg fn lines
stdlib imports: collections
| File | LOC | SLOC | Fns | Complexity | Depth | Imports |
|---|---|---|---|---|---|---|
| ladder.py | 22 | 21 | 1 | 9 | 5 | collections |
ladder.py · 22 lines · 727 B
from collections import deque def ladder_length(begin: str, end: str, word_list: list[str]) -> int: word_set = set(word_list) if end not in word_set: return 0 if begin == end: return 1 queue = deque() queue.append((begin, 1)) visited = set([begin]) while queue: current, steps = queue.popleft() if current == end: return steps for i in range(len(current)): for c in 'abcdefghijklmnopqrstuvwxyz': new_word = current[:i] + c + current[i+1:] if new_word in word_set and new_word not in visited: visited.add(new_word) queue.append((new_word, steps + 1)) return 0
04 how it was graded
1
model calls
0
invalid actions
0
self test runs
4.4k
tokens out
252
tokens in
196.3s
wall time
agent actions: —
final pytest output
..... [100%] 5 passed in 0.02s