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 200k |
|---|---|---|---|---|---|---|
[
{
"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. Let me start by understanding the problem.
We have N programmers, each numbered from 1 to N. There are M relations given, each stating that one programmer is stronger than another. The relations are transitiv... |
[
{
"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 figure out this problem step by step. So, we have 2 moles of Hg(g) being combusted in a fixed volume bomb calorimeter with excess O₂, and it forms HgO(s). The temperature goes up from 298 K to 312.8 K. We need to find the standard molar enthalpy of formation of HgO(s) at 298 K, which is X kJ/... |
[
{
"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 solve this problem where Kevin has to maximize the number of points he earns by rearranging an array of integers. The points are earned when, for each element, after adding it to the sum S, if the result is even, he divides S by 2 repeatedly until it's odd. Each operation can only earn one po... |
[{"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 figure out where the joker can be after each operation in a deck of car(...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 solve this problem where I have 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, 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 there's 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/a1_math_tiger_math_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 18.7 | 58.8 | 77.4 | 26.6 | 35.5 | 45.1 | 17.2 | 3.7 | 5.7 |
AIME24
- Average Accuracy: 18.67% ± 1.17%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.33% | 7 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 13.33% | 4 | 30 |
| 4 | 16.67% | 5 | 30 |
| 5 | 16.67% | 5 | 30 |
| 6 | 16.67% | 5 | 30 |
| 7 | 20.00% | 6 | 30 |
| 8 | 16.67% | 5 | 30 |
| 9 | 26.67% | 8 | 30 |
| 10 | 16.67% | 5 | 30 |
AMC23
- Average Accuracy: 58.75% ± 1.47%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 65.00% | 26 | 40 |
| 2 | 57.50% | 23 | 40 |
| 3 | 62.50% | 25 | 40 |
| 4 | 55.00% | 22 | 40 |
| 5 | 65.00% | 26 | 40 |
| 6 | 52.50% | 21 | 40 |
| 7 | 52.50% | 21 | 40 |
| 8 | 60.00% | 24 | 40 |
| 9 | 62.50% | 25 | 40 |
| 10 | 55.00% | 22 | 40 |
MATH500
- Accuracy: 77.40%
Accuracy Questions Solved Total Questions 77.40% 387 500
MMLUPro
- Average Accuracy: 26.60% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 26.60% | 133 | 500 |
JEEBench
- Average Accuracy: 35.47% ± 0.53%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 35.53% | 183.0 | 515 |
| 2 | 34.32% | 176.75 | 515 |
| 3 | 36.55% | 188.25 | 515 |
GPQADiamond
- Average Accuracy: 45.12% ± 1.69%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 41.92% | 83 | 198 |
| 2 | 44.44% | 88 | 198 |
| 3 | 48.99% | 97 | 198 |
LiveCodeBench
- Average Accuracy: 17.16% ± 0.69%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 17.42% | 89 | 511 |
| 2 | 15.85% | 81 | 511 |
| 3 | 18.20% | 93 | 511 |
CodeElo
- Average Accuracy: 3.67% ± 0.23%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 3.32% | 13 | 391 |
| 2 | 4.09% | 16 | 391 |
| 3 | 3.58% | 14 | 391 |
CodeForces
- Average Accuracy: 5.67% ± 0.63%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 6.40% | 29 | 453 |
| 2 | 4.42% | 20 | 453 |
| 3 | 6.18% | 28 | 453 |
- Downloads last month
- 8