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 1.05k 163k |
|---|---|---|---|---|---|---|
[
{
"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 determine if there's a unique strongest programmer based on given comparisons and transitivity. Let's think about how to approach this.
First, the problem states that the superiority relation is a total order with transitivity. But the given information might ... |
[
{
"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, the question is about calculating the standard molar enthalpy of formation of HgO(s) using the given data. Let me start by writing down all the information provided and what's being asked.
We have 2 moles of Hg(g) combusted in a bomb calorimeter with... |
[
{
"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. I need to find the maximum number of points Kevin can earn by rearranging the array. The points are earned when each a_i (after adding to s) makes s even, and then we divide s by 2 until it's odd. But each operation can only give one point, so the order matters.
Hmm, the editorial says that c_... |
[{"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 by the ESPRESSO spect(...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 find the number o(...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, I need to solve this problem where I have to find the number of incremovable subarra(...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 see. I need to solve this problem where I have to find the earliest time when (...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 after each query, I have to determine if the blac(...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 generate a Python function that reads N from stdin and prints the grid acc(...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_openthoughts_30k_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 26.7 | 65.8 | 83.4 | 29.6 | 43.2 | 39.4 | 30.1 | 9.3 | 12.8 |
AIME24
- Average Accuracy: 26.67% ± 1.33%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.33% | 7 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 26.67% | 8 | 30 |
| 4 | 30.00% | 9 | 30 |
| 5 | 23.33% | 7 | 30 |
| 6 | 33.33% | 10 | 30 |
| 7 | 26.67% | 8 | 30 |
| 8 | 33.33% | 10 | 30 |
| 9 | 23.33% | 7 | 30 |
| 10 | 26.67% | 8 | 30 |
AMC23
- Average Accuracy: 65.75% ± 1.94%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 70.00% | 28 | 40 |
| 2 | 52.50% | 21 | 40 |
| 3 | 70.00% | 28 | 40 |
| 4 | 72.50% | 29 | 40 |
| 5 | 70.00% | 28 | 40 |
| 6 | 62.50% | 25 | 40 |
| 7 | 57.50% | 23 | 40 |
| 8 | 65.00% | 26 | 40 |
| 9 | 70.00% | 28 | 40 |
| 10 | 67.50% | 27 | 40 |
MATH500
- Accuracy: 83.40%
Accuracy Questions Solved Total Questions 83.40% 417 500
MMLUPro
- Average Accuracy: 29.60% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 29.60% | 148 | 500 |
JEEBench
- Average Accuracy: 43.16% ± 0.66%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 44.66% | 230.0 | 515 |
| 2 | 41.89% | 215.75 | 515 |
| 3 | 42.91% | 221.0 | 515 |
GPQADiamond
- Average Accuracy: 39.39% ± 0.48%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 39.39% | 78 | 198 |
| 2 | 38.38% | 76 | 198 |
| 3 | 40.40% | 80 | 198 |
LiveCodeBench
- Average Accuracy: 30.07% ± 0.96%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 28.18% | 144 | 511 |
| 2 | 30.72% | 157 | 511 |
| 3 | 31.31% | 160 | 511 |
CodeElo
- Average Accuracy: 9.29% ± 0.37%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 9.97% | 39 | 391 |
| 2 | 9.21% | 36 | 391 |
| 3 | 8.70% | 34 | 391 |
CodeForces
- Average Accuracy: 12.80% ± 0.56%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 13.91% | 63 | 453 |
| 2 | 12.36% | 56 | 453 |
| 3 | 12.14% | 55 | 453 |
- Downloads last month
- 4