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 9 578k |
|---|---|---|---|---|---|---|
[
{
"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, so I need to write a Python function that takes input from stdin and outputs the strongest programmer based on the given relations. Let me break down the problem step by step.
First, the input is given as N and M, followed by M pairs of (A_i, B_i) indicating that A_i is stronger than B_i. The goal is to ... |
[
{
"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 reaction where 2 moles of Hg(g) are combusted in a bomb calorimeter with excess O2 to form HgO(s). The temperature changes from 298 K to 312.8 K, and I have to use that to find the ... |
[{"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": 1,
"temperature": 0.7
} | 1 | 363 | CodeForces | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | "<think>\nOkay, so the problem is about maximizing the number of points Kevin can earn by rearrangin(...TRUNCATED) |
[{"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
} | \boxed{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 we have a deck of cards and a joker. The joker(...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 solve this problem where I have to find the number of incremovable suba(...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 we have to determine the earliest time when al(...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 I have a tree with vertices colored white or b(...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, so I need to write a Python function that generates a valid arrangement of dragon pa(...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/316_globalbatchsize96_lr1e5_epochs11_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 11.3 | 41.0 | 64.2 | 21.2 | 27.8 | 28.6 | 11.0 | 1.0 | 1.1 |
AIME24
- Average Accuracy: 11.33% ± 1.26%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.67% | 5 | 30 |
| 2 | 10.00% | 3 | 30 |
| 3 | 10.00% | 3 | 30 |
| 4 | 10.00% | 3 | 30 |
| 5 | 3.33% | 1 | 30 |
| 6 | 10.00% | 3 | 30 |
| 7 | 10.00% | 3 | 30 |
| 8 | 10.00% | 3 | 30 |
| 9 | 16.67% | 5 | 30 |
| 10 | 16.67% | 5 | 30 |
AMC23
- Average Accuracy: 41.00% ± 1.91%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 42.50% | 17 | 40 |
| 2 | 45.00% | 18 | 40 |
| 3 | 47.50% | 19 | 40 |
| 4 | 35.00% | 14 | 40 |
| 5 | 27.50% | 11 | 40 |
| 6 | 45.00% | 18 | 40 |
| 7 | 45.00% | 18 | 40 |
| 8 | 42.50% | 17 | 40 |
| 9 | 35.00% | 14 | 40 |
| 10 | 45.00% | 18 | 40 |
MATH500
- Accuracy: 64.20%
Accuracy Questions Solved Total Questions 64.20% 321 500
MMLUPro
- Average Accuracy: 21.20% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 21.20% | 106 | 500 |
JEEBench
- Average Accuracy: 27.78% ± 0.46%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 26.70% | 137.5 | 515 |
| 2 | 28.06% | 144.5 | 515 |
| 3 | 28.59% | 147.25 | 515 |
GPQADiamond
- Average Accuracy: 28.62% ± 5.03%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.23% | 46 | 198 |
| 2 | 21.72% | 43 | 198 |
| 3 | 40.91% | 81 | 198 |
LiveCodeBench
- Average Accuracy: 11.02% ± 1.81%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 10.76% | 55 | 511 |
| 2 | 8.02% | 41 | 511 |
| 3 | 14.29% | 73 | 511 |
CodeElo
- Average Accuracy: 1.02% ± 0.26%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 1.28% | 5 | 391 |
| 2 | 1.28% | 5 | 391 |
| 3 | 0.51% | 2 | 391 |
CodeForces
- Average Accuracy: 1.10% ± 0.44%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 0.66% | 3 | 453 |
| 2 | 1.99% | 9 | 453 |
| 3 | 0.66% | 3 | 453 |
- Downloads last month
- 3