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 233k |
|---|---|---|---|---|---|---|
[
{
"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
} | Here's a Python function to solve the problem based on the given prompt:
```python
def find_strongest():
import sys
input = sys.stdin.read
data = input().split()
n = int(data[0])
m = int(data[1])
edges = []
visited = [False] * (n + 1)
parent = [i for i in range(n + 1)]
rank = [... |
[
{
"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 a combustion reaction of Hg(g) in a bomb calorimeter. Let me try to break this down step by step.
First, the reaction is the combustion of 2 moles of Hg(g) with excess O2(g) to form ... |
[
{
"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
} | Okay, let's try to figure out this problem. So, the problem is called "Kevin and Arithmetic." From the description, Kevin has a sum s that starts at 0. For each number in the list, he adds it to s. If the sum becomes even, he earns a point and keeps dividing it by 2 until it's odd again. The goal is to rearrange the li... |
[
{
"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 with an 8m VLT telescope. The requirement is a signal-to-noise ratio (S/N) of at least 10 per binned pixel during a 1-hour exposure.
First, I should probably understand what factors influence the d... |
[{"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 solve this problem where there's a deck of n cards, a joker at position(...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
} | "<think>\nOkay, so I need to figure out how to count all the subarrays in a given list that, when re(...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 solve this problem where there are n rooms, each with a light initially(...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 vertices colored either bl(...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 Python function that reads the input grid size N, places Takahashi at the center, and arra(...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 need to find the probability that a randomly chosen point inside rectangle ABCD(...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_natural_reasoning_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 18.0 | 59.5 | 78.8 | 28.6 | 39.5 | 48.3 | 15.7 | 2.5 | 4.7 |
AIME24
- Average Accuracy: 18.00% ± 1.17%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.67% | 5 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 20.00% | 6 | 30 |
| 4 | 23.33% | 7 | 30 |
| 5 | 10.00% | 3 | 30 |
| 6 | 20.00% | 6 | 30 |
| 7 | 20.00% | 6 | 30 |
| 8 | 16.67% | 5 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 13.33% | 4 | 30 |
AMC23
- Average Accuracy: 59.50% ± 1.72%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 67.50% | 27 | 40 |
| 2 | 60.00% | 24 | 40 |
| 3 | 60.00% | 24 | 40 |
| 4 | 70.00% | 28 | 40 |
| 5 | 60.00% | 24 | 40 |
| 6 | 52.50% | 21 | 40 |
| 7 | 57.50% | 23 | 40 |
| 8 | 52.50% | 21 | 40 |
| 9 | 55.00% | 22 | 40 |
| 10 | 60.00% | 24 | 40 |
MATH500
- Accuracy: 78.80%
Accuracy Questions Solved Total Questions 78.80% 394 500
MMLUPro
- Average Accuracy: 28.60% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 28.60% | 143 | 500 |
JEEBench
- Average Accuracy: 39.53% ± 0.47%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 40.49% | 208.5 | 515 |
| 2 | 38.50% | 198.25 | 515 |
| 3 | 39.61% | 204.0 | 515 |
GPQADiamond
- Average Accuracy: 48.32% ± 0.90%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 47.47% | 94 | 198 |
| 2 | 50.51% | 100 | 198 |
| 3 | 46.97% | 93 | 198 |
LiveCodeBench
- Average Accuracy: 15.66% ± 0.68%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 15.66% | 80 | 511 |
| 2 | 16.83% | 86 | 511 |
| 3 | 14.48% | 74 | 511 |
CodeElo
- Average Accuracy: 2.47% ± 0.31%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 3.07% | 12 | 391 |
| 2 | 2.30% | 9 | 391 |
| 3 | 2.05% | 8 | 391 |
CodeForces
- Average Accuracy: 4.71% ± 0.39%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 3.97% | 18 | 453 |
| 2 | 4.86% | 22 | 453 |
| 3 | 5.30% | 24 | 453 |
- Downloads last month
- 8