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 259k |
|---|---|---|---|---|---|---|
[
{
"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 figure out the strongest programmer among N people based on given superiority relations. The problem states that each pair of distinct programmers has a defined superiority, and this relation is transitive. The goal is to determine if there's a unique strongest programmer, and if not, output ... |
[
{
"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 try to tackle this problem step by step. First, let me make sure I understand what's being asked here. We have 2 moles of mercury gas (Hg) being combusted in a fixed volume bomb calorimeter with excess oxygen (O₂) at 298 K and 1 atm. The reaction produces mercuric oxide (HgO) solid. The temperature ... |
[
{
"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 me try to figure out this problem. So, Kevin has these numbers, and he adds them one by one to a sum s. If after adding a number, 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 numbers so that the total number of points Kevin can ea... |
[{"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, so I need to figure out how many of these stars would be detectable using the ESPRES(...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, so I need to solve this problem where we have a deck of n cards, with a joker at pos(...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 \"incremovable\" subarrays in the given(...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 multiple rooms with lights that are co(...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 we have a tree with n vertices, each initially(...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 create a function that arranges the dragon parts and Takahashi on an N (...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/b1_math_top_1_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 25.7 | 71.8 | 83.0 | 35.0 | 44.0 | 39.7 | 23.0 | 6.5 | 6.8 |
AIME24
- Average Accuracy: 25.67% ± 2.41%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.33% | 7 | 30 |
| 2 | 30.00% | 9 | 30 |
| 3 | 13.33% | 4 | 30 |
| 4 | 36.67% | 11 | 30 |
| 5 | 26.67% | 8 | 30 |
| 6 | 30.00% | 9 | 30 |
| 7 | 20.00% | 6 | 30 |
| 8 | 30.00% | 9 | 30 |
| 9 | 33.33% | 10 | 30 |
| 10 | 13.33% | 4 | 30 |
AMC23
- Average Accuracy: 71.75% ± 1.80%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 80.00% | 32 | 40 |
| 2 | 75.00% | 30 | 40 |
| 3 | 77.50% | 31 | 40 |
| 4 | 77.50% | 31 | 40 |
| 5 | 62.50% | 25 | 40 |
| 6 | 72.50% | 29 | 40 |
| 7 | 65.00% | 26 | 40 |
| 8 | 65.00% | 26 | 40 |
| 9 | 72.50% | 29 | 40 |
| 10 | 70.00% | 28 | 40 |
MATH500
- Accuracy: 83.00%
Accuracy Questions Solved Total Questions 83.00% 415 500
MMLUPro
- Average Accuracy: 35.00% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 35.00% | 175 | 500 |
JEEBench
- Average Accuracy: 43.98% ± 1.35%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 46.17% | 237.75 | 515 |
| 2 | 40.73% | 209.75 | 515 |
| 3 | 45.05% | 232.0 | 515 |
GPQADiamond
- Average Accuracy: 39.73% ± 0.36%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 39.90% | 79 | 198 |
| 2 | 40.40% | 80 | 198 |
| 3 | 38.89% | 77 | 198 |
LiveCodeBench
- Average Accuracy: 23.03% ± 0.62%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.09% | 118 | 511 |
| 2 | 21.92% | 112 | 511 |
| 3 | 24.07% | 123 | 511 |
CodeElo
- Average Accuracy: 6.48% ± 1.05%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 6.14% | 24 | 391 |
| 2 | 4.86% | 19 | 391 |
| 3 | 8.44% | 33 | 391 |
CodeForces
- Average Accuracy: 6.84% ± 0.89%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 5.30% | 24 | 453 |
| 2 | 8.39% | 38 | 453 |
| 3 | 6.84% | 31 | 453 |
- Downloads last month
- 3