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 147k |
|---|---|---|---|---|---|---|
[
{
"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 solve this programming problem. Let's read the problem carefully.
The problem is about determining the strongest programmer based on given superiority relations. The strongest is the one who is stronger than all others. The superiority is a total order with a transitivity property. So, the key ... |
[
{
"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. The goal is to find the standard molar enthalpy of formation of HgO(s) at 298 K. The problem provides some information about the combustion of Hg(g) and gives us data to calculate this unknown value.
First, let's write down the chemical reaction taking place. The r... |
[
{
"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's see. The problem is about maximizing the points Kevin can earn by rearranging the array. The points are earned when the sum s becomes even at each step. But wait, the key is that after adding a_i to s, if it's even, he earns a point and then divides s by 2 repeatedly until it's odd. So each a_i can ... |
[
{
"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
} | To determine how many of the stars listed would be detectable using the ESPRESSO spectrograph coupled with an 8m VLT telescope, we need to calculate the signal-to-noise ratio (S/N) for each star based on their distance and absolute magnitude. The star is detectable if the S/N is at least 10 per binned pixel during a 1-... |
[{"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, let's tackle this problem. Hmm, the problem is about tracking the possible positions(...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, let's try to figure out how to solve this problem. The task is to find the number of(...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, I need to solve this problem where I have to find the earliest time when all the roo(...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've got this programming problem to solve. Let's read through it carefully.\n\nT(...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, I need to solve this problem where I have to generate a grid with Takahashi placed 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
} | "To solve this problem, we need to determine the probability that a randomly chosen point inside a r(...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_code_contests_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 15.0 | 49.0 | 71.2 | 27.4 | 34.6 | 29.0 | 29.7 | 10.8 | 15.0 |
AIME24
- Average Accuracy: 15.00% ± 1.27%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.67% | 5 | 30 |
| 2 | 13.33% | 4 | 30 |
| 3 | 20.00% | 6 | 30 |
| 4 | 20.00% | 6 | 30 |
| 5 | 10.00% | 3 | 30 |
| 6 | 16.67% | 5 | 30 |
| 7 | 13.33% | 4 | 30 |
| 8 | 10.00% | 3 | 30 |
| 9 | 10.00% | 3 | 30 |
| 10 | 20.00% | 6 | 30 |
AMC23
- Average Accuracy: 49.00% ± 1.70%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 45.00% | 18 | 40 |
| 2 | 52.50% | 21 | 40 |
| 3 | 40.00% | 16 | 40 |
| 4 | 52.50% | 21 | 40 |
| 5 | 60.00% | 24 | 40 |
| 6 | 52.50% | 21 | 40 |
| 7 | 47.50% | 19 | 40 |
| 8 | 45.00% | 18 | 40 |
| 9 | 50.00% | 20 | 40 |
| 10 | 45.00% | 18 | 40 |
MATH500
- Accuracy: 71.20%
Accuracy Questions Solved Total Questions 71.20% 356 500
MMLUPro
- Average Accuracy: 27.40% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 27.40% | 137 | 500 |
JEEBench
- Average Accuracy: 34.64% ± 0.35%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 33.79% | 174.0 | 515 |
| 2 | 35.05% | 180.5 | 515 |
| 3 | 35.10% | 180.75 | 515 |
GPQADiamond
- Average Accuracy: 28.96% ± 0.84%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 28.79% | 57 | 198 |
| 2 | 30.81% | 61 | 198 |
| 3 | 27.27% | 54 | 198 |
LiveCodeBench
- Average Accuracy: 29.75% ± 1.17%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 30.92% | 158 | 511 |
| 2 | 30.92% | 158 | 511 |
| 3 | 27.40% | 140 | 511 |
CodeElo
- Average Accuracy: 10.83% ± 0.95%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 12.02% | 47 | 391 |
| 2 | 11.51% | 45 | 391 |
| 3 | 8.95% | 35 | 391 |
CodeForces
- Average Accuracy: 15.01% ± 0.22%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 15.45% | 70 | 453 |
| 2 | 14.79% | 67 | 453 |
| 3 | 14.79% | 67 | 453 |
- Downloads last month
- 3