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 52 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
} | from collections import defaultdict
def find_strongest():
N, M = map(int, input().split())
relations = defaultdict(set)
for _ in range(M):
A, B = map(int, input().split())
relations[A].add(B)
relations[B].add(A)
strongest = None
for person in range(1, N + 1):
if all... |
[
{
"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 calorimeter experiment where mercury vapor is combusted with excess oxygen, and the temperature change is measured. Let me start by writing down the relevant information and the che... |
[
{
"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, so I need to figure out this problem called "Kevin and Arithmetic." Let me start by understanding the problem statement properly.
**Problem Statement**:
- Given an array of integers **a** and a sum **s** initialized to 0.
- For each integer **a_i** in the array (from index 1 to n), do the following:
1. Add **... |
[
{
"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, so I need to figure out how many of these stars would be detectable using the ESPRESSO spectrograph on the VLT telescopes at Paranal. The key criterion is achieving a signal-to-noise ratio (S/N) of at least 10 per binned pixel during a 1-hour exposure. Let's start by recalling what factors influence the S... |
[{"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
} | "Alright, let's tackle this problem step by step. So, the problem is about a deck of cards with a jo(...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
} | "def count_incremovable_subarrays(nums):\n n = len(nums)\n count = 0\n\n for start in range(...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
} | "To solve this problem, we need to determine the earliest time when all lights in an apartment are t(...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
} | "To solve this problem, I need to track the color of each node and determine after each toggle query(...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
} | "def solve():\n import sys\n input = sys.stdin.readline\n\n def print_grid(grid):\n (...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 determine the probability that a randomly chosen point inside rectangle \\(ABCD\\) is closer to (...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_science_wikipedia_field_of_science_1744716441_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 15.3 | 54.0 | 73.8 | 26.0 | 36.4 | 38.6 | 4.0 | 4.0 | 6.4 |
AIME24
- Average Accuracy: 15.33% ± 1.26%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 13.33% | 4 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 16.67% | 5 | 30 |
| 4 | 13.33% | 4 | 30 |
| 5 | 20.00% | 6 | 30 |
| 6 | 6.67% | 2 | 30 |
| 7 | 20.00% | 6 | 30 |
| 8 | 13.33% | 4 | 30 |
| 9 | 16.67% | 5 | 30 |
| 10 | 13.33% | 4 | 30 |
AMC23
- Average Accuracy: 54.00% ± 1.42%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 60.00% | 24 | 40 |
| 2 | 52.50% | 21 | 40 |
| 3 | 60.00% | 24 | 40 |
| 4 | 50.00% | 20 | 40 |
| 5 | 55.00% | 22 | 40 |
| 6 | 57.50% | 23 | 40 |
| 7 | 47.50% | 19 | 40 |
| 8 | 52.50% | 21 | 40 |
| 9 | 47.50% | 19 | 40 |
| 10 | 57.50% | 23 | 40 |
MATH500
- Accuracy: 73.80%
Accuracy Questions Solved Total Questions 73.80% 369 500
MMLUPro
- Average Accuracy: 26.00% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 26.00% | 130 | 500 |
JEEBench
- Average Accuracy: 36.42% ± 1.69%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 32.57% | 167.75 | 515 |
| 2 | 39.66% | 204.25 | 515 |
| 3 | 37.04% | 190.75 | 515 |
GPQADiamond
- Average Accuracy: 38.55% ± 0.36%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 38.38% | 76 | 198 |
| 2 | 37.88% | 75 | 198 |
| 3 | 39.39% | 78 | 198 |
LiveCodeBench
- Average Accuracy: 3.98% ± 0.46%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.89% | 25 | 511 |
| 2 | 3.52% | 18 | 511 |
| 3 | 3.52% | 18 | 511 |
CodeElo
- Average Accuracy: 4.01% ± 0.23%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.09% | 16 | 391 |
| 2 | 4.35% | 17 | 391 |
| 3 | 3.58% | 14 | 391 |
CodeForces
- Average Accuracy: 6.40% ± 0.96%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.64% | 21 | 453 |
| 2 | 7.95% | 36 | 453 |
| 3 | 6.62% | 30 | 453 |
- Downloads last month
- 12