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
1.8k
320k
[ { "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, so I need to generate a Python function that takes a list of numbers and an integer k, then returns the sum of the elements at indices where the number of set bits (1s) in the binary representation of the index is exactly k. Hmm. Let me think about how to approach this. First, I need to iterate over each...
[ { "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 after removing n/2 elements from each of two arrays. The set is formed by the remaining elements from both arrays. Hmm, let's think through this step by step. First, the problem is to maximize the size of the set s. Sinc...
[ { "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 first, I need to understand how these numbers are formed and how their sums work. Hmm, let's start by thi...
[{"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, so I need to generate a Python function that takes input from stdin, computes the pro(...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 solve this problem where I have to find the minimum number of coins to b(...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 place Takahashi at the center of an N x (...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, so I need to solve this programming problem. Let's read the problem carefully again.\(...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 determine the order of books to read (...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 adjust the purchase amount to the neares(...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_ckpt02500_eval_27e9

Precomputed model outputs for evaluation.

Evaluation Results

LiveCodeBench

  • Average Accuracy: 45.96% ± 0.56%
  • Number of Runs: 6
Run Accuracy Questions Solved Total Questions
1 47.75% 244 511
2 45.60% 233 511
3 43.64% 223 511
4 46.38% 237 511
5 45.79% 234 511
6 46.58% 238 511
Downloads last month
8