context listlengths 1 1 | gen_kwargs dict | repeat_idx int64 0 9 | request_idx int64 0 514 | task_name stringclasses 9
values | metadata dict | model_outputs stringlengths 1 193k |
|---|---|---|---|---|---|---|
[
{
"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.There are N competitive programmers numbered person 1, person 2, \\ldots, and person N.\nThere is a relation called su... | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 256 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | from collections import defaultdict
def find_strongest_programmer():
import sys
input = sys.stdin.read
data = input().split()
N = int(data[0])
M = int(data[1])
# Create graph and in-degree
graph = defaultdict(list)
in_degree = [0] * N
for i in range(M):
A = in... |
[
{
"content": "In this problem, the final will be a numeric value. Give the numerical answer correct upto the 2nd decimal digit. Give a detailed solution and end the solution with the final answer. Mark your solution with \\boxed\nAnswer:\n\nProblem: 2 mol of $\\mathrm{Hg}(g)$ is combusted in a fixed volume bomb... | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 2,
"temperature": 0.7
} | 2 | 400 | JEEBench | {
"expected_answer": "90.39",
"problem_id": "37",
"reference_solution": null,
"subject": "chem",
"type": "Numeric"
} | <think>
Okay, so I need to find the standard molar enthalpy of formation of HgO(s) using the information given. Let me start by recalling what enthalpy of formation means. The enthalpy of formation is the change in enthalpy when one mole of a compound is formed from its elements in their standard states. In this case, ... |
[
{
"content": "You are a coding expert. Given a competition-level coding problem, you need to write a Python program to solve it. You may start by outlining your thought process. In the end, please provide the complete code in a code block enclosed with ``` ```. The code should take stdin as input and print the ... | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 1,
"temperature": 0.7
} | 1 | 363 | CodeForces | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | <think>
Okay, so I need to solve this problem where Kevin has to maximize the number of points by rearranging the integers. The points are earned when he adds an even number to the sum s, and after adding, he keeps dividing s by 2 until it becomes odd. Each operation can only give a point once, even if s is divided mul... |
[
{
"content": "Return your final response within \\boxed{} and only include the letter choice (A, B, C, or D) as your final response.\nProblem: How many of the stars listed below would be detectable using the ESPRESSO spectrograph, when it is coupled with one of the 8m VLT telescopes at the Paranal Observatory? ... | {
"do_sample": true,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 186 | GPQADiamond | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | <think>
Okay, so I need to figure out how many of these stars listed would be detectable using the ESPRESSO spectrograph on the VLT telescopes at Paranal. The key requirement is achieving a signal-to-noise ratio (S/N) of at least 10 per binned pixel during a 1-hour exposure. Let me start by recalling what I know about ... |
[
{
"content": "You are a coding expert. Given a competition-level coding problem, you need to write a Python program to solve it. You may start by outlining your thought process. In the end, please provide the complete code in a code block enclosed with ``` ```. The code should take stdin as input and print the ... | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 321 | CodeForces | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | <think>
Okay, so I need to solve this problem where there's a deck of n cards, a joker at position m, and q operations are performed. Each operation takes a card from position a_i and moves it either to the beginning or the end of the deck. After each operation, I need to find the number of distinct positions where the... |
[
{
"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 array of positive integers nums.\nA subarray of nums is called incremovable if nums becomes strictly increasing on removing the subar... | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 2,
"temperature": 0.7
} | 2 | 167 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | To determine the number of incremovable subarrays in a given array `nums`, we need to check all possible subarrays and see if removing them results in a strictly increasing array. Here's a step-by-step approach to solve this problem:
1. **Generate All Subarrays**: Iterate through all possible starting and ending indic... |
[{"content":"\"You are a coding expert. Given a competition-level coding problem, you need to write (...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 2,
"temperature": 0.7
} | 2 | 152 | CodeElo | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | "Alright, let's tackle this light switches problem. The goal is to find the earliest time when all t(...TRUNCATED) |
[{"content":"\"You are a coding expert. Given a competition-level coding problem, you need to write (...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 31 | CodeElo | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | "<think>\nOkay, so I need to solve this problem where there's a tree with n vertices, each initially(...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 | 359 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | "<execute>\nAlright, let's see. I need to create a Python function that arranges Takahashi and the d(...TRUNCATED) |
[{"content":"Problem: Rectangle $ABCD$ has center $O$ and $AB/AD=k$. A point is randomly chosen from(...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 444 | MATH500 | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | "<think>\nOkay, so I have this problem about a rectangle ABCD with center O, and the sides AB and AD(...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/a1_science_cqadupstack_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 18.7 | 60.0 | 77.0 | 28.8 | 45.4 | 42.8 | 12.2 | 4.4 | 5.7 |
AIME24
- Average Accuracy: 18.67% ± 1.26%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 10.00% | 3 | 30 |
| 2 | 16.67% | 5 | 30 |
| 3 | 16.67% | 5 | 30 |
| 4 | 23.33% | 7 | 30 |
| 5 | 20.00% | 6 | 30 |
| 6 | 16.67% | 5 | 30 |
| 7 | 23.33% | 7 | 30 |
| 8 | 16.67% | 5 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 23.33% | 7 | 30 |
AMC23
- Average Accuracy: 60.00% ± 1.73%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 65.00% | 26 | 40 |
| 2 | 50.00% | 20 | 40 |
| 3 | 55.00% | 22 | 40 |
| 4 | 62.50% | 25 | 40 |
| 5 | 60.00% | 24 | 40 |
| 6 | 55.00% | 22 | 40 |
| 7 | 67.50% | 27 | 40 |
| 8 | 60.00% | 24 | 40 |
| 9 | 67.50% | 27 | 40 |
| 10 | 57.50% | 23 | 40 |
MATH500
- Accuracy: 77.00%
Accuracy Questions Solved Total Questions 77.00% 385 500
MMLUPro
- Average Accuracy: 28.80% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 28.80% | 144 | 500 |
JEEBench
- Average Accuracy: 45.42% ± 0.17%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 45.00% | 231.75 | 515 |
| 2 | 45.63% | 235.0 | 515 |
| 3 | 45.63% | 235.0 | 515 |
GPQADiamond
- Average Accuracy: 42.76% ± 1.82%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 41.92% | 83 | 198 |
| 2 | 46.97% | 93 | 198 |
| 3 | 39.39% | 78 | 198 |
LiveCodeBench
- Average Accuracy: 12.20% ± 0.43%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 12.52% | 64 | 511 |
| 2 | 11.35% | 58 | 511 |
| 3 | 12.72% | 65 | 511 |
CodeElo
- Average Accuracy: 4.43% ± 0.60%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 5.37% | 21 | 391 |
| 2 | 4.60% | 18 | 391 |
| 3 | 3.32% | 13 | 391 |
CodeForces
- Average Accuracy: 5.67% ± 0.57%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.64% | 21 | 453 |
| 2 | 5.74% | 26 | 453 |
| 3 | 6.62% | 30 | 453 |
- Downloads last month
- 4