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 182k |
|---|---|---|---|---|---|---|
[
{
"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
} | import sys
def find_strongest_programmer(N, M, relations):
# Convert the list of relations into a graph
graph = {i: set() for i in range(1, N + 1)}
for A, B in relations:
graph[A].add(B)
graph[B].add(A)
# Check if there's a cycle in the graph (which would mean multiple strongest progra... |
[
{
"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 figure out the standard molar enthalpy of formation of HgO(s) at 298 K. The problem involves combusting 2 mol of Hg(g) in a fixed volume bomb calorimeter with excess O2. The temperature increases from 298 K to 312.8 K. They also gave the heat capacity of the bomb calorimeter as 20.00 kJ K-1 a... |
[
{
"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
} | To solve this problem, we need to determine the maximum number of points Kevin can earn by rearranging the integers \( a_1, a_2, \ldots, a_n \). The key steps are as follows:
1. **Understanding the Operation**:
- For each integer \( a_i \), Kevin adds it to the current sum \( s \).
- If the resulting \( s \) is ... |
[
{
"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 are detectable using the ESPRESSO spectrograph when paired with an 8-meter VLT telescope at Paranal. The key requirement is that the signal-to-noise ratio (S/N) must be at least 10 per binned pixel after a 1-hour exposure.
First, let me recall what factors... |
[
{
"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
} | Alright, let's tackle this coding problem step by step. So, we have a deck of n cards with a joker at position m. We perform q operations where each operation moves the card at position a_i either to the top or the bottom of the deck. The goal is to determine the number of distinct positions the joker can be in after e... |
[{"content":"Generate an executable Python function generated from the given prompt. Return the func(...TRUNCATED) | {
"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
} | "<think>\nOkay, so I need to figure out how to count the number of incremovable subarrays in a given(...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": 2,
"temperature": 0.7
} | 2 | 152 | CodeElo | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | "To solve the problem of determining the earliest moment when all rooms have their lights turned on,(...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 we have a tree of n vertices, each initially c(...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
} | "Here's a possible solution for the problem. The function takes an integer N as input and prints the(...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
} | "To solve the problem of finding the probability that a randomly chosen point inside rectangle \\(AB(...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_math_allenai_math_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 15.7 | 50.3 | 73.2 | 26.2 | 31.5 | 36.7 | 7.2 | 2.6 | 5.0 |
AIME24
- Average Accuracy: 15.67% ± 1.06%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 13.33% | 4 | 30 |
| 2 | 16.67% | 5 | 30 |
| 3 | 20.00% | 6 | 30 |
| 4 | 23.33% | 7 | 30 |
| 5 | 13.33% | 4 | 30 |
| 6 | 16.67% | 5 | 30 |
| 7 | 13.33% | 4 | 30 |
| 8 | 13.33% | 4 | 30 |
| 9 | 13.33% | 4 | 30 |
| 10 | 13.33% | 4 | 30 |
AMC23
- Average Accuracy: 50.25% ± 1.30%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 52.50% | 21 | 40 |
| 2 | 45.00% | 18 | 40 |
| 3 | 52.50% | 21 | 40 |
| 4 | 45.00% | 18 | 40 |
| 5 | 57.50% | 23 | 40 |
| 6 | 47.50% | 19 | 40 |
| 7 | 45.00% | 18 | 40 |
| 8 | 52.50% | 21 | 40 |
| 9 | 52.50% | 21 | 40 |
| 10 | 52.50% | 21 | 40 |
MATH500
- Accuracy: 73.20%
Accuracy Questions Solved Total Questions 73.20% 366 500
MMLUPro
- Average Accuracy: 26.20% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 26.20% | 131 | 500 |
JEEBench
- Average Accuracy: 31.49% ± 0.59%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 32.52% | 167.5 | 515 |
| 2 | 31.84% | 164.0 | 515 |
| 3 | 30.10% | 155.0 | 515 |
GPQADiamond
- Average Accuracy: 36.70% ± 2.02%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 31.82% | 63 | 198 |
| 2 | 39.90% | 79 | 198 |
| 3 | 38.38% | 76 | 198 |
LiveCodeBench
- Average Accuracy: 7.18% ± 0.73%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 6.26% | 32 | 511 |
| 2 | 8.61% | 44 | 511 |
| 3 | 6.65% | 34 | 511 |
CodeElo
- Average Accuracy: 2.64% ± 0.34%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 2.30% | 9 | 391 |
| 2 | 2.30% | 9 | 391 |
| 3 | 3.32% | 13 | 391 |
CodeForces
- Average Accuracy: 5.00% ± 0.07%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.86% | 22 | 453 |
| 2 | 5.08% | 23 | 453 |
| 3 | 5.08% | 23 | 453 |
- Downloads last month
- 4