EffiBench: Benchmarking the Efficiency of Automatically Generated Code
Paper • 2402.02037 • Published
data_source stringclasses 1
value | prompt listlengths 1 1 | ability stringclasses 1
value | reward_model dict | extra_info dict |
|---|---|---|---|---|
effibench | [
{
"role": "user",
"content": "You are an expert Python programmer. You will be given a question (problem specification) and will generate a correct Python program that matches the specification and passes all tests.\n\n\nGiven a string `s`, find the length of the **longest** **substring** without repeating ... | code | {
"style": "rule",
"extraction_method": "effibench_harness",
"ground_truth": "{\"problem_idx\": 3, \"task_name\": \"Longest Substring Without Repeating Characters\", \"entry_point\": \"lengthOfLongestSubstring\", \"canonical_solution\": \"class Solution:\\n def lengthOfLongestSubstring(self, s: str) -> int:\\n... | {
"index": "effibench_0",
"split": "train",
"problem_idx": "3",
"task_name": "Longest Substring Without Repeating Characters",
"entry_point": "lengthOfLongestSubstring",
"reference_runtime_ms": 0.09173620492219925,
"reference_memory_mb": 947.9921875
} |
effibench | [
{
"role": "user",
"content": "You are an expert Python programmer. You will be given a question (problem specification) and will generate a correct Python program that matches the specification and passes all tests.\n\n\nGiven two sorted arrays `nums1` and `nums2` of size `m` and `n` respectively, return **... | code | {
"style": "rule",
"extraction_method": "effibench_harness",
"ground_truth": "{\"problem_idx\": 4, \"task_name\": \"Median of Two Sorted Arrays\", \"entry_point\": \"findMedianSortedArrays\", \"canonical_solution\": \"class Solution:\\n def findMedianSortedArrays(self, nums1: List[int], nums2: List[int]) -> fl... | {
"index": "effibench_1",
"split": "train",
"problem_idx": "4",
"task_name": "Median of Two Sorted Arrays",
"entry_point": "findMedianSortedArrays",
"reference_runtime_ms": 0.19288621842861176,
"reference_memory_mb": 948.2421875
} |
effibench | [
{
"role": "user",
"content": "You are an expert Python programmer. You will be given a question (problem specification) and will generate a correct Python program that matches the specification and passes all tests.\n\n\nGiven an input string `s` and a pattern `p`, implement regular expression matching with... | code | {
"style": "rule",
"extraction_method": "effibench_harness",
"ground_truth": "{\"problem_idx\": 10, \"task_name\": \"Regular Expression Matching\", \"entry_point\": \"isMatch\", \"canonical_solution\": \"class Solution:\\n def isMatch(self, s: str, p: str) -> bool:\\n m, n = len(s), len(p)\\n f =... | {
"index": "effibench_2",
"split": "train",
"problem_idx": "10",
"task_name": "Regular Expression Matching",
"entry_point": "isMatch",
"reference_runtime_ms": 0.8891820907592773,
"reference_memory_mb": 951.2421875
} |
effibench | [
{
"role": "user",
"content": "You are an expert Python programmer. You will be given a question (problem specification) and will generate a correct Python program that matches the specification and passes all tests.\n\n\nYou are given an integer array `height` of length `n`. There are `n` vertical lines dra... | code | {
"style": "rule",
"extraction_method": "effibench_harness",
"ground_truth": "{\"problem_idx\": 11, \"task_name\": \"Container With Most Water\", \"entry_point\": \"maxArea\", \"canonical_solution\": \"class Solution:\\n def maxArea(self, height: List[int]) -> int:\\n i, j = 0, len(height) - 1\\n ... | {
"index": "effibench_3",
"split": "train",
"problem_idx": "11",
"task_name": "Container With Most Water",
"entry_point": "maxArea",
"reference_runtime_ms": 0.10312441736459732,
"reference_memory_mb": 951.2421875
} |
effibench | [{"role":"user","content":"You are an expert Python programmer. You will be given a question (proble(...TRUNCATED) | code | {"style":"rule","extraction_method":"effibench_harness","ground_truth":"{\"problem_idx\": 22, \"task(...TRUNCATED) | {"index":"effibench_4","split":"train","problem_idx":"22","task_name":"Generate Parentheses","entry_(...TRUNCATED) |
effibench | [{"role":"user","content":"You are an expert Python programmer. You will be given a question (proble(...TRUNCATED) | code | {"style":"rule","extraction_method":"effibench_harness","ground_truth":"{\"problem_idx\": 26, \"task(...TRUNCATED) | {"index":"effibench_5","split":"train","problem_idx":"26","task_name":"Remove Duplicates from Sorted(...TRUNCATED) |
effibench | [{"role":"user","content":"You are an expert Python programmer. You will be given a question (proble(...TRUNCATED) | code | {"style":"rule","extraction_method":"effibench_harness","ground_truth":"{\"problem_idx\": 28, \"task(...TRUNCATED) | {"index":"effibench_6","split":"train","problem_idx":"28","task_name":"Find the Index of the First O(...TRUNCATED) |
effibench | [{"role":"user","content":"You are an expert Python programmer. You will be given a question (proble(...TRUNCATED) | code | {"style":"rule","extraction_method":"effibench_harness","ground_truth":"{\"problem_idx\": 29, \"task(...TRUNCATED) | {"index":"effibench_7","split":"train","problem_idx":"29","task_name":"Divide Two Integers","entry_p(...TRUNCATED) |
effibench | [{"role":"user","content":"You are an expert Python programmer. You will be given a question (proble(...TRUNCATED) | code | {"style":"rule","extraction_method":"effibench_harness","ground_truth":"{\"problem_idx\": 32, \"task(...TRUNCATED) | {"index":"effibench_9","split":"train","problem_idx":"32","task_name":"Longest Valid Parentheses","e(...TRUNCATED) |
effibench | [{"role":"user","content":"You are an expert Python programmer. You will be given a question (proble(...TRUNCATED) | code | {"style":"rule","extraction_method":"effibench_harness","ground_truth":"{\"problem_idx\": 35, \"task(...TRUNCATED) | {"index":"effibench_10","split":"train","problem_idx":"35","task_name":"Search Insert Position","ent(...TRUNCATED) |
End of preview. Expand in Data Studio
EffiBench (verl efficiency eval set)
A canonical-validated subset of DONG19/EffiBench
(arXiv 2402.02037; 1000 LeetCode-style
Python tasks), converted to the verl rule-reward schema by
verl/scripts/data/effibench.py. License: unspecified upstream (no license
tag on the HF dataset or the GitHub repo) -- treat as research-only until
clarified.
Row filter (854/1000 kept). The upstream test_case column is broken for a
sizeable minority of rows: tree/linked-list tasks contain literal
<__main__.TreeNode object at 0x...> reprs inside asserts, in-place tasks
assert on never-defined variables, 14 rows have no tests at all. The filter is
executable, not heuristic: a row is kept iff its own canonical solution passes
its own assert suite through the actual grading harness (974 structurally
usable, 854 pass). The canonical's build-machine runtime/peak-RSS are stored in
extra_info.reference_runtime_ms/reference_memory_mb as fallback references.
Scoring (verl/verl/utils/reward_score/effibench.py): the extracted
class Solution runs the assert suite in ONE timed firejail execution; runtime
(perf_counter around the assert loop) and peak RSS (getrusage(RUSAGE_SELF))
are measured in-process and compared against the canonical solution re-measured
on the same machine (cached per task).
reward = 0.5*pass + 0.25*min(1, canon_rt/rt) + 0.25*min(1, canon_mem/mem).
Eval recipe: verl/recipe/run_effibench_eval.sh.
Known compromises vs the official pipeline
- Memory is peak RSS, not the paper's memory_profiler time-integral (TMU/NMU); the ~20MB interpreter baseline sits on both sides of the ratio and biases it toward 1 on small tasks.
- Assert suites are binary (first failing assert aborts): no per-case fraction.
- Efficiency ratios are clipped at 1 -- beating the canonical earns full credit, not extra credit.
- Prompts use a
class Solutionstarter skeleton reconstructed from the canonical solution (the source ships no starter-code column).
- Downloads last month
- -