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 1.4k 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 the strongest programmer among N people based on the given relations. The problem states that each pair of distinct programmers has a defined superiority, and this relation is transitive. The strongest programmer is someone who is stronger than everyone else. If there are multiple ... |
[
{
"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 at 298 K, and it forms HgO(s). The temperature goes from 298.0 K to 312.8 K. We need to find the standard molar enthalpy of formation of HgO(s) at 298 K, which ... |
[
{
"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 step by step. So, the problem is about Kevin and his arithmetic skills. His mother wants to maximize the number of points he earns by rearranging the given integers. Let me parse the problem again to make sure I understand it correctly.
Each integer operation adds a_... |
[{"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 (Canopus, Polaris, and four othe(...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 the deck. The(...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 solve this problem where there are n rooms, each with a light that's in(...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>\nAlright, let's see. I need to create a Python function that generates a grid with N rows a(...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_4_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 23.0 | 63.2 | 81.8 | 29.2 | 44.6 | 38.2 | 19.4 | 4.0 | 3.6 |
AIME24
- Average Accuracy: 23.00% ± 0.57%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.33% | 7 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 23.33% | 7 | 30 |
| 4 | 23.33% | 7 | 30 |
| 5 | 23.33% | 7 | 30 |
| 6 | 26.67% | 8 | 30 |
| 7 | 23.33% | 7 | 30 |
| 8 | 23.33% | 7 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 23.33% | 7 | 30 |
AMC23
- Average Accuracy: 63.25% ± 1.73%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 65.00% | 26 | 40 |
| 2 | 67.50% | 27 | 40 |
| 3 | 57.50% | 23 | 40 |
| 4 | 72.50% | 29 | 40 |
| 5 | 52.50% | 21 | 40 |
| 6 | 65.00% | 26 | 40 |
| 7 | 65.00% | 26 | 40 |
| 8 | 60.00% | 24 | 40 |
| 9 | 67.50% | 27 | 40 |
| 10 | 60.00% | 24 | 40 |
MATH500
- Accuracy: 81.80%
Accuracy Questions Solved Total Questions 81.80% 409 500
MMLUPro
- Average Accuracy: 29.20% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 29.20% | 146 | 500 |
JEEBench
- Average Accuracy: 44.63% ± 0.59%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 46.07% | 237.25 | 515 |
| 2 | 43.88% | 226.0 | 515 |
| 3 | 43.93% | 226.25 | 515 |
GPQADiamond
- Average Accuracy: 38.22% ± 0.69%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 37.37% | 74 | 198 |
| 2 | 37.37% | 74 | 198 |
| 3 | 39.90% | 79 | 198 |
LiveCodeBench
- Average Accuracy: 19.37% ± 0.49%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 18.98% | 97 | 511 |
| 2 | 20.35% | 104 | 511 |
| 3 | 18.79% | 96 | 511 |
CodeElo
- Average Accuracy: 4.01% ± 0.23%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.09% | 16 | 391 |
| 2 | 4.35% | 17 | 391 |
| 3 | 3.58% | 14 | 391 |
CodeForces
- Average Accuracy: 3.61% ± 0.27%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 3.09% | 14 | 453 |
| 2 | 3.75% | 17 | 453 |
| 3 | 3.97% | 18 | 453 |
- Downloads last month
- 5