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 1.55k 726k |
|---|---|---|---|---|---|---|
[
{
"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, I need to solve this problem where I have to find out if there's a unique strongest programmer based on the given relations. Let's think about how to approach this.
First, the problem says that the superiority is transitive. So, if A is stronger than B, and B is stronger than C, then A is stronger than C... |
[
{
"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 mol of Hg(g) is combusted in a bomb calorimeter with excess O₂, leading to HgO(s). The temperature increases from 298 K to 312.8 K, and I have the heat capacity of ... |
[
{
"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's see. The problem is to rearrange the array a so that Kevin earns the maximum number of points. The way the points are earned is when adding an a_i to s makes it even, then we divide s by 2 until it's odd. But each operation can only contribute at most one point, even if you can divide multiple times... |
[{"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've got this astronomy problem here. It's about determining how many stars from (...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, I need to solve this problem where after each operation, I have to track the possibl(...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, let's try to figure out how to solve this problem. So the task is to find the total (...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, let's try to figure out how to solve this problem. So the task is to find the earlie(...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, I need to solve this problem where I have to track whether all the black vertices fo(...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, I need to solve this problem where I have to place dragon parts in an N x N grid wit(...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_scaling_bespoke_stratos_1k_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 14.3 | 53.5 | 72.0 | 27.2 | 37.1 | 37.4 | 25.0 | 4.3 | 5.8 |
AIME24
- Average Accuracy: 14.33% ± 0.95%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 20.00% | 6 | 30 |
| 2 | 13.33% | 4 | 30 |
| 3 | 16.67% | 5 | 30 |
| 4 | 16.67% | 5 | 30 |
| 5 | 10.00% | 3 | 30 |
| 6 | 10.00% | 3 | 30 |
| 7 | 13.33% | 4 | 30 |
| 8 | 13.33% | 4 | 30 |
| 9 | 16.67% | 5 | 30 |
| 10 | 13.33% | 4 | 30 |
AMC23
- Average Accuracy: 53.50% ± 1.18%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 55.00% | 22 | 40 |
| 2 | 57.50% | 23 | 40 |
| 3 | 52.50% | 21 | 40 |
| 4 | 50.00% | 20 | 40 |
| 5 | 47.50% | 19 | 40 |
| 6 | 50.00% | 20 | 40 |
| 7 | 52.50% | 21 | 40 |
| 8 | 57.50% | 23 | 40 |
| 9 | 52.50% | 21 | 40 |
| 10 | 60.00% | 24 | 40 |
MATH500
- Accuracy: 72.00%
Accuracy Questions Solved Total Questions 72.00% 360 500
MMLUPro
- Average Accuracy: 27.20% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 27.20% | 136 | 500 |
JEEBench
- Average Accuracy: 37.06% ± 0.54%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 38.30% | 197.25 | 515 |
| 2 | 36.07% | 185.75 | 515 |
| 3 | 36.80% | 189.5 | 515 |
GPQADiamond
- Average Accuracy: 37.37% ± 1.56%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 37.88% | 75 | 198 |
| 2 | 40.40% | 80 | 198 |
| 3 | 33.84% | 67 | 198 |
LiveCodeBench
- Average Accuracy: 25.05% ± 0.92%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 24.66% | 126 | 511 |
| 2 | 23.68% | 121 | 511 |
| 3 | 26.81% | 137 | 511 |
CodeElo
- Average Accuracy: 4.26% ± 0.47%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.60% | 18 | 391 |
| 2 | 4.86% | 19 | 391 |
| 3 | 3.32% | 13 | 391 |
CodeForces
- Average Accuracy: 5.81% ± 0.52%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 6.62% | 30 | 453 |
| 2 | 5.96% | 27 | 453 |
| 3 | 4.86% | 22 | 453 |
- Downloads last month
- 4