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 1.78k 233k |
|---|---|---|---|---|---|---|
[
{
"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 the strongest programmer among N people based on the given M relationships. The key points here are that the relationships form a tournament graph (since every pair has exactly one direction) and the transitivity must hold. The strongest programmer is... |
[
{
"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 combustion experiment in a bomb calorimeter. Let me try to parse all the details step by step.
First, the problem states that 2 moles of Hg(g) are combusted in a fixed volume bomb ... |
[
{
"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 solve this problem where Kevin is trying to maximize the points by rearranging the array of numbers. The points are earned when after adding a_i to s, s becomes even, and then we divide by 2 until it's odd. But each operation can give at most one point, so each time you can only get 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> Okay, so I need to figure out how many of these stars can be detected 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> Okay, I need to solve this problem where after each operation, I have to find the number of(...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> Okay, I need to solve this problem where I have to find the number of incremovable subarray(...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> Okay, so I need to solve this problem where we have rooms with lights that are toggled by c(...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> Okay, I need to solve this problem where I have a tree of vertices, and I have to handle qu(...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> Okay, I need to solve this problem where I have to generate a grid with Takahashi in the ce(...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> Okay, so I have this problem about a rectangle ABCD with center O, and the ratio of AB to A(...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/openthoughts3_herorun_ckpt05000_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 65.0 | 91.0 | 89.0 | 0.4 | 62.9 | 44.3 | 55.4 | 24.5 | 27.2 |
AIME24
- Average Accuracy: 65.00% ± 1.58%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 60.00% | 18 | 30 |
| 2 | 56.67% | 17 | 30 |
| 3 | 70.00% | 21 | 30 |
| 4 | 60.00% | 18 | 30 |
| 5 | 60.00% | 18 | 30 |
| 6 | 66.67% | 20 | 30 |
| 7 | 66.67% | 20 | 30 |
| 8 | 70.00% | 21 | 30 |
| 9 | 70.00% | 21 | 30 |
| 10 | 70.00% | 21 | 30 |
AMC23
- Average Accuracy: 91.00% ± 0.81%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 90.00% | 36 | 40 |
| 2 | 92.50% | 37 | 40 |
| 3 | 95.00% | 38 | 40 |
| 4 | 87.50% | 35 | 40 |
| 5 | 92.50% | 37 | 40 |
| 6 | 87.50% | 35 | 40 |
| 7 | 92.50% | 37 | 40 |
| 8 | 92.50% | 37 | 40 |
| 9 | 87.50% | 35 | 40 |
| 10 | 92.50% | 37 | 40 |
MATH500
- Accuracy: 89.00%
Accuracy Questions Solved Total Questions 89.00% 445 500
MMLUPro
- Accuracy: 0.37%
Accuracy Questions Solved Total Questions 0.37% N/A N/A
JEEBench
- Average Accuracy: 62.93% ± 0.49%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 63.35% | 326.25 | 515 |
| 2 | 61.75% | 318.0 | 515 |
| 3 | 63.69% | 328.0 | 515 |
GPQADiamond
- Average Accuracy: 44.28% ± 0.36%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 44.44% | 88 | 198 |
| 2 | 43.43% | 86 | 198 |
| 3 | 44.95% | 89 | 198 |
LiveCodeBench
- Average Accuracy: 55.38% ± 0.69%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 56.75% | 290 | 511 |
| 2 | 54.60% | 279 | 511 |
| 3 | 54.79% | 280 | 511 |
CodeElo
- Average Accuracy: 24.47% ± 0.73%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.02% | 90 | 391 |
| 2 | 25.32% | 99 | 391 |
| 3 | 25.06% | 98 | 391 |
CodeForces
- Average Accuracy: 27.23% ± 1.76%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 30.68% | 139 | 453 |
| 2 | 24.94% | 113 | 453 |
| 3 | 26.05% | 118 | 453 |
- Downloads last month
- 3