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 170k |
|---|---|---|---|---|---|---|
[
{
"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 programming problem. Let's read the problem carefully.
So the problem is about determining the strongest programmer based on given comparisons. The strongest is the one who is stronger than all others. But the relations between the programmers are given, and we have to check if there... |
[
{
"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 finding the standard molar enthalpy of formation of mercury oxide (HgO) using the data provided. The problem involves a combustion reaction in a bomb calorimeter, and we need to calculate the enthalpy change for the formation 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 about maximizing the number of points Kevin earns by rearranging the array of integers. The operations are for each element in the array, add it to the sum s. Then, if s is even, he earns a point and keeps dividing s by 2 until it's odd again. The goal is to find the maximum poss... |
[
{
"content": "Return your final response within \\boxed{} and only include the letter choice (A, B, C, or D) as your final response.\nProblem: How many of the stars listed below would be detectable using the ESPRESSO spectrograph, when it is coupled with one of the 8m VLT telescopes at the Paranal Observatory? ... | {
"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, let's try to figure out how many of these stars are detectable with ESPRESSO on the VLT. The key is the signal-to-noise ratio (S/N) needing to be at least 10 per binned pixel in a 1-hour exposure.
First, I need to recall what factors affect the S/N. The S/N for a star in a long-exposure spectrograph is ... |
[{"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 try to figure out how to solve this problem. So the problem is about light swi(...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 toggle query, I have to check if all t(...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, let's see. I need to create a Python function that generates a grid for a given odd (...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 have this problem about a rectangle with center O, and the sides AB and AD have(...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/reasoning_6_chat_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 28.3 | 69.0 | 83.8 | 28.4 | 49.8 | 38.9 | 37.3 | 10.4 | 15.7 |
AIME24
- Average Accuracy: 28.33% ± 1.72%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 30.00% | 9 | 30 |
| 2 | 23.33% | 7 | 30 |
| 3 | 30.00% | 9 | 30 |
| 4 | 26.67% | 8 | 30 |
| 5 | 33.33% | 10 | 30 |
| 6 | 20.00% | 6 | 30 |
| 7 | 36.67% | 11 | 30 |
| 8 | 33.33% | 10 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 30.00% | 9 | 30 |
AMC23
- Average Accuracy: 69.00% ± 1.47%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 67.50% | 27 | 40 |
| 2 | 75.00% | 30 | 40 |
| 3 | 62.50% | 25 | 40 |
| 4 | 70.00% | 28 | 40 |
| 5 | 60.00% | 24 | 40 |
| 6 | 70.00% | 28 | 40 |
| 7 | 75.00% | 30 | 40 |
| 8 | 70.00% | 28 | 40 |
| 9 | 72.50% | 29 | 40 |
| 10 | 67.50% | 27 | 40 |
MATH500
- Accuracy: 83.80%
Accuracy Questions Solved Total Questions 83.80% 419 500
MMLUPro
- Average Accuracy: 28.40% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 28.40% | 142 | 500 |
JEEBench
- Average Accuracy: 49.84% ± 0.29%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 50.24% | 258.75 | 515 |
| 2 | 49.13% | 253.0 | 515 |
| 3 | 50.15% | 258.25 | 515 |
GPQADiamond
- Average Accuracy: 38.89% ± 1.33%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 35.86% | 71 | 198 |
| 2 | 41.41% | 82 | 198 |
| 3 | 39.39% | 78 | 198 |
LiveCodeBench
- Average Accuracy: 37.31% ± 0.91%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 35.81% | 183 | 511 |
| 2 | 38.94% | 199 | 511 |
| 3 | 37.18% | 190 | 511 |
CodeElo
- Average Accuracy: 10.40% ± 0.67%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 11.51% | 45 | 391 |
| 2 | 10.49% | 41 | 391 |
| 3 | 9.21% | 36 | 391 |
CodeForces
- Average Accuracy: 15.67% ± 0.25%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.11% | 73 | 453 |
| 2 | 15.67% | 71 | 453 |
| 3 | 15.23% | 69 | 453 |
- Downloads last month
- 32