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 143k |
|---|---|---|---|---|---|---|
[
{
"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
} | ```python
def determine_strongest_programmer():
import sys
input = sys.stdin.read
data = input().split()
N = int(data[0])
M = int(data[1])
superiorities = {}
for i in range(M):
A = int(data[2*i + 2]) - 1
B = int(data[2*i + 3]) - 1
if (A, B) not in superiorit... |
[
{
"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) at 298 K. The problem gives me some information about the combustion of Hg(g) in a bomb calorimeter with excess O2. Let me try to break this down step by step.
First, the reaction is Hg(g) + O2(g) → HgO(s). Since it's a standard enthalp... |
[
{
"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, let me try to figure out this problem. So, the problem is about Kevin and his arithmetic skills. His mother wants to rearrange the numbers in a way that maximizes the number of points Kevin can earn. Each time Kevin adds a number to the sum 's', and if the resulting sum is even, he earns a point and keeps... |
[
{
"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 here is that the signal-to-noise ratio (S/N) needs to be at least 10 per binned pixel during a 1-hour exposure.
First, I should recall what factors affect ... |
[{"content":"You are a coding expert. Given a competition-level coding problem, you need to write a (...TRUNCATED) | {
"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>\nOkay, so I need to figure out where the joker can be after each operation in this deck shu(...TRUNCATED) |
[{"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
} | "```python\ndef count_incremovable_subarrays(nums):\n n = len(nums)\n count = 0\n\n for sta(...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
} | "<think>\nOkay, so I need to figure out the earliest time when all the lights in the apartment are o(...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
} | "```python\ndef place_dragon_parts(n):\n # Initialize the grid with zeros\n grid = [[0 for _ i(...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 ratio of AB to (...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_gair_math_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 21.7 | 64.2 | 79.4 | 32.4 | 43.8 | 45.5 | 18.5 | 7.5 | 8.7 |
AIME24
- Average Accuracy: 21.67% ± 1.35%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.67% | 5 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 23.33% | 7 | 30 |
| 4 | 23.33% | 7 | 30 |
| 5 | 16.67% | 5 | 30 |
| 6 | 26.67% | 8 | 30 |
| 7 | 23.33% | 7 | 30 |
| 8 | 20.00% | 6 | 30 |
| 9 | 16.67% | 5 | 30 |
| 10 | 30.00% | 9 | 30 |
AMC23
- Average Accuracy: 64.25% ± 1.06%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 57.50% | 23 | 40 |
| 2 | 67.50% | 27 | 40 |
| 3 | 65.00% | 26 | 40 |
| 4 | 60.00% | 24 | 40 |
| 5 | 67.50% | 27 | 40 |
| 6 | 62.50% | 25 | 40 |
| 7 | 67.50% | 27 | 40 |
| 8 | 65.00% | 26 | 40 |
| 9 | 67.50% | 27 | 40 |
| 10 | 62.50% | 25 | 40 |
MATH500
- Accuracy: 79.40%
Accuracy Questions Solved Total Questions 79.40% 397 500
MMLUPro
- Average Accuracy: 32.40% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 32.40% | 162 | 500 |
JEEBench
- Average Accuracy: 43.83% ± 1.28%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 46.31% | 238.5 | 515 |
| 2 | 44.27% | 228.0 | 515 |
| 3 | 40.92% | 210.75 | 515 |
GPQADiamond
- Average Accuracy: 45.45% ± 1.72%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 49.49% | 98 | 198 |
| 2 | 42.42% | 84 | 198 |
| 3 | 44.44% | 88 | 198 |
LiveCodeBench
- Average Accuracy: 18.46% ± 1.65%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.44% | 84 | 511 |
| 2 | 17.22% | 88 | 511 |
| 3 | 21.72% | 111 | 511 |
CodeElo
- Average Accuracy: 7.50% ± 0.96%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 7.42% | 29 | 391 |
| 2 | 5.88% | 23 | 391 |
| 3 | 9.21% | 36 | 391 |
CodeForces
- Average Accuracy: 8.68% ± 0.78%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 8.39% | 38 | 453 |
| 2 | 7.51% | 34 | 453 |
| 3 | 10.15% | 46 | 453 |
- Downloads last month
- 4