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 425 187k |
|---|---|---|---|---|---|---|
[
{
"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, let's see. I need to find the strongest programmer based on the given comparisons. 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. The strongest is the one who is stronger than all others. If there's a tie, output -1.
H... |
[
{
"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 tackle this problem step by step. Hmm, the problem is asking for the standard molar enthalpy of formation of HgO(s) at 298 K. The given data includes the temperature change, heat capacity of the bomb calorimeter, and the enthalpy of formation of Hg(g). Oh right, and we need to find the absolute valu... |
[
{
"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 can get by rearranging the array of integers. The way points are earned is when adding a number to the sum s (which starts at 0) makes it even, and then he divides it by 2 repeatedly until it's odd. Each addition of a number counts as a... |
[
{
"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
} | To determine how many of the stars listed would be detectable using the ESPRESSO spectrograph coupled with an 8m VLT telescope, we need to calculate the signal-to-noise ratio (S/N) for each star. The star is detectable if the S/N per binned pixel during a 1-hour exposure is at least 10.
First, let's recall the formula... |
[{"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, let's tackle this problem. Hmm, the problem is about tracking the possible positions(...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 see. I need to find the number of incremovable subarrays in a given array of p(...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 tackle this problem. Hmm, the problem is about finding 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 check if all 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 solve this problem where I have to arrange Takahashi and the dragon parts (...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
} | "To solve this problem, we need to determine the probability that a randomly chosen point inside rec(...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/a1_code_apps_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 19.0 | 58.5 | 71.8 | 28.6 | 36.6 | 35.0 | 29.4 | 7.1 | 10.3 |
AIME24
- Average Accuracy: 19.00% ± 1.16%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 13.33% | 4 | 30 |
| 2 | 23.33% | 7 | 30 |
| 3 | 20.00% | 6 | 30 |
| 4 | 16.67% | 5 | 30 |
| 5 | 13.33% | 4 | 30 |
| 6 | 16.67% | 5 | 30 |
| 7 | 20.00% | 6 | 30 |
| 8 | 23.33% | 7 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 23.33% | 7 | 30 |
AMC23
- Average Accuracy: 58.50% ± 1.33%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 65.00% | 26 | 40 |
| 2 | 55.00% | 22 | 40 |
| 3 | 57.50% | 23 | 40 |
| 4 | 60.00% | 24 | 40 |
| 5 | 65.00% | 26 | 40 |
| 6 | 60.00% | 24 | 40 |
| 7 | 57.50% | 23 | 40 |
| 8 | 52.50% | 21 | 40 |
| 9 | 60.00% | 24 | 40 |
| 10 | 52.50% | 21 | 40 |
MATH500
- Accuracy: 71.80%
Accuracy Questions Solved Total Questions 71.80% 359 500
MMLUPro
- Average Accuracy: 28.60% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 28.60% | 143 | 500 |
JEEBench
- Average Accuracy: 36.57% ± 0.18%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 36.99% | 190.5 | 515 |
| 2 | 36.26% | 186.75 | 515 |
| 3 | 36.46% | 187.75 | 515 |
GPQADiamond
- Average Accuracy: 35.02% ± 1.55%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 31.82% | 63 | 198 |
| 2 | 38.38% | 76 | 198 |
| 3 | 34.85% | 69 | 198 |
LiveCodeBench
- Average Accuracy: 29.42% ± 1.19%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 29.35% | 150 | 511 |
| 2 | 27.40% | 140 | 511 |
| 3 | 31.51% | 161 | 511 |
CodeElo
- Average Accuracy: 7.08% ± 0.70%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 6.14% | 24 | 391 |
| 2 | 8.44% | 33 | 391 |
| 3 | 6.65% | 26 | 391 |
CodeForces
- Average Accuracy: 10.30% ± 1.08%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 12.14% | 55 | 453 |
| 2 | 8.39% | 38 | 453 |
| 3 | 10.38% | 47 | 453 |
- Downloads last month
- 3