Dataset Viewer
Auto-converted to Parquet Duplicate
context
listlengths
1
1
gen_kwargs
dict
repeat_idx
int64
0
5
request_idx
int64
0
510
task_name
stringclasses
1 value
metadata
dict
model_outputs
stringlengths
2.44k
260k
[ { "content": "Generate an executable Python function generated from the given prompt. Return the function body without invoking it at the final solution.You are given a 0-indexed integer array nums and an integer k.\nReturn an integer that denotes the sum of elements in nums whose corresponding indices have exa...
{ "do_sample": false, "max_new_tokens": 32768, "seed": 3, "temperature": 0.7 }
3
106
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "" }
<think> Okay, I need to solve this problem where I have to find the sum of elements in an array based on their indices' binary representations. Let me see... The task is to return the sum of all nums[i] where the number of set bits (1s) in the binary representation of i is exactly k. Oh right, the indices are 0-based. ...
[ { "content": "Generate an executable Python function generated from the given prompt. Return the function body without invoking it at the final solution.You are given two 0-indexed integer arrays nums1 and nums2 of even length n.\nYou must remove n / 2 elements from nums1 and n / 2 elements from nums2. After th...
{ "do_sample": false, "max_new_tokens": 32768, "seed": 5, "temperature": 0.7 }
5
150
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "" }
<think> Okay, I need to solve this problem where I have to find the maximum possible size of a set formed after removing n/2 elements from each of the two arrays, and then inserting the remaining elements into a set. The key here is to maximize the number of unique elements in the combined set. Hmm, let me think. The...
[ { "content": "Generate an executable Python function generated from the given prompt. The function should take stdin as input and print the output. Simply call the function after the definition.A repunit is an integer whose digits are all 1 in decimal representation. The repunits in ascending order are 1, 11, 1...
{ "do_sample": false, "max_new_tokens": 32768, "seed": 5, "temperature": 0.7 }
5
348
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "" }
<think> Okay, I need to solve this problem where I have to find the N-th smallest number that can be written as the sum of exactly three repunits. Repunits are numbers like 1, 11, 111, etc., all made up of 1's. So the task is, given N, output the N-th such number in order. Hmm, let me think. The first thing I should f...
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 3, "temperature": 0.7 }
3
410
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "" }
"<think> Okay, I need to write a Python function that takes N integers as input and outputs the prod(...TRUNCATED)
[{"content":"Generate an executable Python function generated from the given prompt. Return the func(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 3, "temperature": 0.7 }
3
137
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "" }
"<think> Okay, so I need to figure out how to solve this problem. Let me read the problem again care(...TRUNCATED)
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 3, "temperature": 0.7 }
3
320
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "" }
"<think> Okay, so I need to solve this problem where Takahashi wants to choose some contests to maxi(...TRUNCATED)
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 4, "temperature": 0.7 }
4
359
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "" }
"<think> Okay, I need to solve this problem where I have to arrange dragon parts in an N x N grid wi(...TRUNCATED)
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 1, "temperature": 0.7 }
1
260
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "" }
"<think> Okay, let's see. I need to solve this problem where after performing certain right circular(...TRUNCATED)
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 2, "temperature": 0.7 }
2
268
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "" }
"<think> Okay, so I need to solve this problem where I have to find the minimal sequence of books to(...TRUNCATED)
[{"content":"Generate an executable Python function generated from the given prompt. Return the func(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 5, "temperature": 0.7 }
5
83
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "" }
"<think> Okay, I need to solve this problem where I have to calculate the final bank account balance(...TRUNCATED)
End of preview. Expand in Data Studio

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

mlfoundations-dev/openthoughts3_herorun_ckpt05500_new_eval_27e9

Precomputed model outputs for evaluation.

Evaluation Results

LiveCodeBench

  • Average Accuracy: 55.51% ± 0.72%
  • Number of Runs: 6
Run Accuracy Questions Solved Total Questions
1 58.71% 300 511
2 56.16% 287 511
3 55.19% 282 511
4 54.21% 277 511
5 53.82% 275 511
6 54.99% 281 511
Downloads last month
4