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 8 169k |
|---|---|---|---|---|---|---|
[
{
"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
} | <think>
Okay, I need to write a Python function that determines the strongest programmer from the given input. Let me think about how to approach this.
First, the problem states that there's a transitive superiority relation. So if A is stronger than B, and B is stronger than C, then A is stronger than C. The stronges... |
[
{
"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, let's tackle this problem step by step. So, the problem is about calculating the standard molar enthalpy of formation of HgO(s) at 298 K. We're given some data, and we need to find the value of X in the answer. Let's see what's provided.
First, we have 2 mol of Hg(g) being combusted in a fixed volume bom... |
[
{
"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
} | </html>
To solve this problem, we need to determine the maximum number of points Kevin can earn by rearranging the given integers. The points are earned when the sum \( s \) becomes even after adding an even number, and Kevin repeatedly divides \( s \) by 2 until it becomes odd. The key insight is to maximize the numb... |
[
{
"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, I need to figure out how many of the given stars can be detected by the ESPRESSO spectrograph when used with an 8m VLT telescope at Paranal. The key condition is achieving an S/N ratio of at least 10 per binned pixel in a 1-hour exposure.
First, I should recall how the signal-to-noise ratio (S/N) is calc... |
[{"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, I need to solve this problem where after each operation, I have to find the number o(...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, I need to solve this problem where I have to find the number of incremovable subarra(...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
} | "Okay, I need to solve this problem where I have to find the earliest moment when all lights are tur(...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, I need to solve this Chain Queries problem. Let's start by understanding the problem(...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
} | "<think>\nOkay, let's see. I need to create a Python function that solves this grid arrangement prob(...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 this problem, we need to determine the probability that a randomly chosen point inside rec(...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_code_octopack_sft_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 16.0 | 53.2 | 71.6 | 26.4 | 37.5 | 41.8 | 25.3 | 5.1 | 6.1 |
AIME24
- Average Accuracy: 16.00% ± 1.03%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.67% | 5 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 16.67% | 5 | 30 |
| 4 | 13.33% | 4 | 30 |
| 5 | 10.00% | 3 | 30 |
| 6 | 16.67% | 5 | 30 |
| 7 | 20.00% | 6 | 30 |
| 8 | 13.33% | 4 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 13.33% | 4 | 30 |
AMC23
- Average Accuracy: 53.25% ± 1.42%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 50.00% | 20 | 40 |
| 2 | 57.50% | 23 | 40 |
| 3 | 57.50% | 23 | 40 |
| 4 | 57.50% | 23 | 40 |
| 5 | 57.50% | 23 | 40 |
| 6 | 45.00% | 18 | 40 |
| 7 | 55.00% | 22 | 40 |
| 8 | 55.00% | 22 | 40 |
| 9 | 47.50% | 19 | 40 |
| 10 | 50.00% | 20 | 40 |
MATH500
- Accuracy: 71.60%
Accuracy Questions Solved Total Questions 71.60% 358 500
MMLUPro
- Average Accuracy: 26.40% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 26.40% | 132 | 500 |
JEEBench
- Average Accuracy: 37.51% ± 0.82%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 36.17% | 186.25 | 515 |
| 2 | 36.89% | 190.0 | 515 |
| 3 | 39.47% | 203.25 | 515 |
GPQADiamond
- Average Accuracy: 41.75% ± 2.96%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 37.88% | 75 | 198 |
| 2 | 38.38% | 76 | 198 |
| 3 | 48.99% | 97 | 198 |
LiveCodeBench
- Average Accuracy: 25.31% ± 0.73%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.87% | 122 | 511 |
| 2 | 25.83% | 132 | 511 |
| 3 | 26.22% | 134 | 511 |
CodeElo
- Average Accuracy: 5.12% ± 0.15%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.86% | 19 | 391 |
| 2 | 5.37% | 21 | 391 |
| 3 | 5.12% | 20 | 391 |
CodeForces
- Average Accuracy: 6.11% ± 0.70%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 7.28% | 33 | 453 |
| 2 | 6.18% | 28 | 453 |
| 3 | 4.86% | 22 | 453 |
- Downloads last month
- 4