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 1.08k 158k |
|---|---|---|---|---|---|---|
[
{
"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 if there's a unique strongest programmer based on the given information. The problem says that if X is stronger than Y and Y is stronger than Z, then X is stronger than Z. That's transitivity, so the relations form a total order. But the catch is that if there's any ambiguity in th... |
[
{
"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. The temperature goes up from 298 K to 312.8 K, and the heat capacity of the bomb calorimeter is 2... |
[
{
"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, so I need to figure out how to maximize the number of points Kevin can earn by rearranging the integers. The points are earned when, during each operation, the current number added to the sum s makes s even. Then, he keeps dividing s by 2 until it becomes odd. Each operation can only give one point, so if... |
[{"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 six stars are detectable by the ESPRESSO 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, so I need to figure out how the joker's possible positions change after each operati(...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 a given list (...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 figure out the earliest time when all the lights in the apartment are t(...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 dragon parts in an N x N grid where N 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
} | "<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/fig1_math_openr1_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 37.3 | 76.8 | 85.0 | 29.8 | 52.0 | 46.0 | 20.2 | 5.0 | 5.4 |
AIME24
- Average Accuracy: 37.33% ± 1.23%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 33.33% | 10 | 30 |
| 2 | 40.00% | 12 | 30 |
| 3 | 30.00% | 9 | 30 |
| 4 | 33.33% | 10 | 30 |
| 5 | 40.00% | 12 | 30 |
| 6 | 36.67% | 11 | 30 |
| 7 | 43.33% | 13 | 30 |
| 8 | 36.67% | 11 | 30 |
| 9 | 40.00% | 12 | 30 |
| 10 | 40.00% | 12 | 30 |
AMC23
- Average Accuracy: 76.75% ± 1.37%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 80.00% | 32 | 40 |
| 2 | 77.50% | 31 | 40 |
| 3 | 75.00% | 30 | 40 |
| 4 | 75.00% | 30 | 40 |
| 5 | 80.00% | 32 | 40 |
| 6 | 85.00% | 34 | 40 |
| 7 | 77.50% | 31 | 40 |
| 8 | 70.00% | 28 | 40 |
| 9 | 77.50% | 31 | 40 |
| 10 | 70.00% | 28 | 40 |
MATH500
- Accuracy: 85.00%
Accuracy Questions Solved Total Questions 85.00% 425 500
MMLUPro
- Average Accuracy: 29.80% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 29.80% | 149 | 500 |
JEEBench
- Average Accuracy: 52.04% ± 0.30%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 52.77% | 271.75 | 515 |
| 2 | 51.60% | 265.75 | 515 |
| 3 | 51.75% | 266.5 | 515 |
GPQADiamond
- Average Accuracy: 45.96% ± 0.82%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 44.95% | 89 | 198 |
| 2 | 47.98% | 95 | 198 |
| 3 | 44.95% | 89 | 198 |
LiveCodeBench
- Average Accuracy: 20.16% ± 0.74%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 20.35% | 104 | 511 |
| 2 | 21.33% | 109 | 511 |
| 3 | 18.79% | 96 | 511 |
CodeElo
- Average Accuracy: 5.03% ± 0.23%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 5.37% | 21 | 391 |
| 2 | 4.60% | 18 | 391 |
| 3 | 5.12% | 20 | 391 |
CodeForces
- Average Accuracy: 5.37% ± 0.64%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 5.52% | 25 | 453 |
| 2 | 4.19% | 19 | 453 |
| 3 | 6.40% | 29 | 453 |
- Downloads last month
- 15