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 157k |
|---|---|---|---|---|---|---|
[
{
"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 the given M relations of who is stronger. The problem is asking for a Python function that takes N and M as input, along with the list of pairs (A_i, B_i) indicating that A_i is stronger than B_i. The output should be the number of t... |
[
{
"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 the reaction, the temperature change, and some other constants. Let me try to break this down step by step.
First, the reaction is the combustion of Hg(g) in a fixed volume bomb calo... |
[
{
"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
} | Okay, so I need to figure out this problem where Kevin is adding numbers to a sum s, and if the sum becomes even, he earns a point and keeps dividing by 2 until it's odd again. The goal is to rearrange the given numbers to maximize the number of points Kevin can earn.
Let me start by understanding the problem step by... |
[{"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 are detectable using the ESPRESSO sp(...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 when performing (...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 many subarrays in the given list `nums` are \"incremovab(...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 moment when all the lights in the apartment are(...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 Python function that generates a valid arrangement of dragon p(...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_baai_infinity_math_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 14.7 | 53.2 | 74.8 | 27.8 | 33.7 | 39.4 | 15.5 | 2.5 | 4.1 |
AIME24
- Average Accuracy: 14.67% ± 1.58%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 13.33% | 4 | 30 |
| 2 | 13.33% | 4 | 30 |
| 3 | 20.00% | 6 | 30 |
| 4 | 13.33% | 4 | 30 |
| 5 | 10.00% | 3 | 30 |
| 6 | 16.67% | 5 | 30 |
| 7 | 23.33% | 7 | 30 |
| 8 | 20.00% | 6 | 30 |
| 9 | 10.00% | 3 | 30 |
| 10 | 6.67% | 2 | 30 |
AMC23
- Average Accuracy: 53.25% ± 1.28%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 55.00% | 22 | 40 |
| 2 | 52.50% | 21 | 40 |
| 3 | 57.50% | 23 | 40 |
| 4 | 45.00% | 18 | 40 |
| 5 | 55.00% | 22 | 40 |
| 6 | 52.50% | 21 | 40 |
| 7 | 50.00% | 20 | 40 |
| 8 | 55.00% | 22 | 40 |
| 9 | 50.00% | 20 | 40 |
| 10 | 60.00% | 24 | 40 |
MATH500
- Accuracy: 74.80%
Accuracy Questions Solved Total Questions 74.80% 374 500
MMLUPro
- Average Accuracy: 27.80% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 27.80% | 139 | 500 |
JEEBench
- Average Accuracy: 33.67% ± 0.27%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 34.03% | 175.25 | 515 |
| 2 | 33.98% | 175.0 | 515 |
| 3 | 33.01% | 170.0 | 515 |
GPQADiamond
- Average Accuracy: 39.39% ± 0.24%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 39.90% | 79 | 198 |
| 2 | 39.39% | 78 | 198 |
| 3 | 38.89% | 77 | 198 |
LiveCodeBench
- Average Accuracy: 15.46% ± 0.68%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.63% | 85 | 511 |
| 2 | 15.46% | 79 | 511 |
| 3 | 14.29% | 73 | 511 |
CodeElo
- Average Accuracy: 2.47% ± 0.31%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 3.07% | 12 | 391 |
| 2 | 2.05% | 8 | 391 |
| 3 | 2.30% | 9 | 391 |
CodeForces
- Average Accuracy: 4.12% ± 0.15%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 3.97% | 18 | 453 |
| 2 | 4.42% | 20 | 453 |
| 3 | 3.97% | 18 | 453 |
- Downloads last month
- 9