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 203k |
|---|---|---|---|---|---|---|
[
{
"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 problem where I have to find the strongest programmer among N people based on M relations. The relations are transitive, so if A is stronger than B and B is stronger than C, then A is stronger than C. The output should be the strongest person's number if there's exactly one, otherwise... |
[
{
"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) using the given data. Let me start by recalling what the enthalpy of formation is. It's the enthalpy change when one mole of a compound is formed from its elements in their standard states. In this case, the reaction is the combustion of... |
[
{
"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. I need to solve this problem where Kevin can maximize the number of points by rearranging the array in a way that allows him to earn points as many times as possible. The points are earned when adding an even number to the sum s, which then gets divided by 2 until it's odd. So each time you add... |
[{"content":"Return your final response within \\boxed{} and only include the letter choice (A, B, C(...TRUNCATED) | {
"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>\nOkay, let's tackle this problem step by step. The question is asking how many of the six s(...TRUNCATED) |
[{"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 we have a deck of cards, a joker at position m, a(...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 see. I need to find all the subarrays that are incremovable. A subarray is con(...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, let's see. I need to solve this problem where there are n rooms, each with a chip in(...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 see. The problem is about maintain(...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 generates a grid where Takahashi (...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_automathtext_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 22.3 | 62.7 | 81.4 | 29.4 | 47.3 | 46.0 | 15.9 | 3.8 | 6.3 |
AIME24
- Average Accuracy: 22.33% ± 1.42%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 20.00% | 6 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 20.00% | 6 | 30 |
| 4 | 26.67% | 8 | 30 |
| 5 | 30.00% | 9 | 30 |
| 6 | 23.33% | 7 | 30 |
| 7 | 13.33% | 4 | 30 |
| 8 | 26.67% | 8 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 23.33% | 7 | 30 |
AMC23
- Average Accuracy: 62.75% ± 0.90%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 60.00% | 24 | 40 |
| 2 | 60.00% | 24 | 40 |
| 3 | 57.50% | 23 | 40 |
| 4 | 62.50% | 25 | 40 |
| 5 | 65.00% | 26 | 40 |
| 6 | 62.50% | 25 | 40 |
| 7 | 65.00% | 26 | 40 |
| 8 | 65.00% | 26 | 40 |
| 9 | 67.50% | 27 | 40 |
| 10 | 62.50% | 25 | 40 |
MATH500
- Accuracy: 81.40%
Accuracy Questions Solved Total Questions 81.40% 407 500
MMLUPro
- Average Accuracy: 29.40% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 29.40% | 147 | 500 |
JEEBench
- Average Accuracy: 47.27% ± 0.49%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 48.40% | 249.25 | 515 |
| 2 | 46.36% | 238.75 | 515 |
| 3 | 47.04% | 242.25 | 515 |
GPQADiamond
- Average Accuracy: 45.96% ± 1.56%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 42.42% | 84 | 198 |
| 2 | 46.46% | 92 | 198 |
| 3 | 48.99% | 97 | 198 |
LiveCodeBench
- Average Accuracy: 15.92% ± 1.70%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 17.81% | 91 | 511 |
| 2 | 17.42% | 89 | 511 |
| 3 | 12.52% | 64 | 511 |
CodeElo
- Average Accuracy: 3.84% ± 0.59%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.86% | 19 | 391 |
| 2 | 2.81% | 11 | 391 |
| 3 | 3.84% | 15 | 391 |
CodeForces
- Average Accuracy: 6.25% ± 0.37%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 5.52% | 25 | 453 |
| 2 | 6.62% | 30 | 453 |
| 3 | 6.62% | 30 | 453 |
- Downloads last month
- 7