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 9 179k |
|---|---|---|---|---|---|---|
[
{
"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 figure out how to determine the strongest programmer based on the given inputs. Let me think about the problem.
First, the constraints: N can be up to 50, and M can be up to N(N-1)/2, which for N=50 is 1225. But wait, the sample inputs have M=6 when N=6, which is okay since 6(6-1)/2=15, so 6 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"
} | To solve this problem, we need to determine the standard molar enthalpy of formation of HgO(s) at 298 K. Let's start by understanding the given information and the steps required.
First, the reaction is the combustion of Hg(g) with O2 to form HgO(s). The balanced equation would be:
\[ 2 \text{Hg}(g) + \text{O}_2(g) \... |
[
{
"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
} | Okay, I need to help Kevin's mom by rearranging the numbers to maximize the points. From the problem statement, the key is to understand how the points are earned.
So, the operation works like this: for each a_i, add it to s. If after adding, s is even, Kevin gets a point and keeps dividing by 2 until it's odd. So th... |
[
{
"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, I need to figure out how many of these stars are detectable using the ESPRESSO spectrograph with the VLT telescopes. The key is to understand the signal-to-noise ratio (S/N) requirement of 10 per binned pixel after a 1-hour exposure.
First, let me recall what affects the S/N in spectroscopy. The S/N is t... |
[
{
"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": 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 we have a deck of cards, a joker at position m, and q operations that move a card to the top or bottom. The task is to track the possible positions the joker can be after each operation.
First, I need to understand how the joker's position changes with each move. Let's ... |
[
{
"content": "Generate an executable Python function generated from the given prompt. Return the function body without invoking it at the final solution.You are given a 0-indexed array of positive integers nums.\nA subarray of nums is called incremovable if nums becomes strictly increasing on removing the subar... | {
"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
} | def count_incremovable_subarrays(nums):
n = len(nums)
count = 0
for i in range(n):
for j in range(i, n):
subarray = nums[i:j+1]
# Check if removing this subarray makes nums strictly increasing
modified = nums[:i] + nums[j+1:]
is_incremovable = True
... |
[{"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, I need to solve this problem where each room has a light that's toggled by a chip in(...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 we have a tree with vertices that can be toggled (...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
} | "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_primeintellect_real_world_swe_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 12.3 | 52.2 | 72.4 | 24.4 | 36.3 | 38.6 | 15.9 | 7.8 | 8.4 |
AIME24
- Average Accuracy: 12.33% ± 1.42%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.33% | 7 | 30 |
| 2 | 10.00% | 3 | 30 |
| 3 | 10.00% | 3 | 30 |
| 4 | 16.67% | 5 | 30 |
| 5 | 13.33% | 4 | 30 |
| 6 | 10.00% | 3 | 30 |
| 7 | 10.00% | 3 | 30 |
| 8 | 6.67% | 2 | 30 |
| 9 | 10.00% | 3 | 30 |
| 10 | 13.33% | 4 | 30 |
AMC23
- Average Accuracy: 52.25% ± 2.22%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 52.50% | 21 | 40 |
| 2 | 50.00% | 20 | 40 |
| 3 | 52.50% | 21 | 40 |
| 4 | 45.00% | 18 | 40 |
| 5 | 40.00% | 16 | 40 |
| 6 | 65.00% | 26 | 40 |
| 7 | 55.00% | 22 | 40 |
| 8 | 50.00% | 20 | 40 |
| 9 | 50.00% | 20 | 40 |
| 10 | 62.50% | 25 | 40 |
MATH500
- Accuracy: 72.40%
Accuracy Questions Solved Total Questions 72.40% 362 500
MMLUPro
- Average Accuracy: 24.40% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 24.40% | 122 | 500 |
JEEBench
- Average Accuracy: 36.31% ± 1.42%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 33.20% | 171.0 | 515 |
| 2 | 36.50% | 188.0 | 515 |
| 3 | 39.22% | 202.0 | 515 |
GPQADiamond
- Average Accuracy: 38.55% ± 0.14%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 38.38% | 76 | 198 |
| 2 | 38.38% | 76 | 198 |
| 3 | 38.89% | 77 | 198 |
LiveCodeBench
- Average Accuracy: 15.92% ± 0.56%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 15.46% | 79 | 511 |
| 2 | 17.03% | 87 | 511 |
| 3 | 15.26% | 78 | 511 |
CodeElo
- Average Accuracy: 7.84% ± 0.37%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 7.93% | 31 | 391 |
| 2 | 7.16% | 28 | 391 |
| 3 | 8.44% | 33 | 391 |
CodeForces
- Average Accuracy: 8.39% ± 0.34%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 7.95% | 36 | 453 |
| 2 | 8.17% | 37 | 453 |
| 3 | 9.05% | 41 | 453 |
- Downloads last month
- 28