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 366k |
|---|---|---|---|---|---|---|
[
{
"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
} | ```python
def find_strongest_programmer():
import sys
input = sys.stdin.readline
N, M = map(int, input().split())
graph = {i: set() for i in range(1, N+1)}
for _ in range(M):
A, B = map(int, input().split())
graph[A].add(B)
graph[B].add(A)
def dfs(node, visited):
... |
[
{
"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 the reaction where mercury vapor is combusted with excess oxygen to form mercury oxide. Let me try to break this down step by step.
First, the reaction is 2 moles of Hg(g) reacting w... |
[
{
"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, let's try to figure out this problem. So, we have to maximize the number of points Kevin can earn by rearranging the integers. The key here is understanding when Kevin can earn a point and how rearranging affects the outcome.
From the problem statement, Kevin earns a point if he adds an even number to s and then... |
[
{
"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 which stars are detectable with ESPRESSO on the VLT, we need to calculate the signal-to-noise ratio (S/N) for each star. The key factors are the star's absolute magnitude, distance, exposure time, and the sensitivity of the instrument.
First, recall that absolute magnitude (M_v) is related to apparent mag... |
[{"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
} | "Okay, let's tackle this problem step by step. So, we have a deck of n cards with a joker at positio(...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
} | "```python\ndef count_incremovable_subarrays(nums):\n n = len(nums)\n count = 0\n for start(...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, so I need to figure out how to solve this problem where there are multiple rooms eac(...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, so I need to solve this problem where I have a tree with vertices colored either bla(...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, so I need to write a Python function that generates a grid of size N x N where N is (...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 ABCD with center O, and the ratio of AB 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/b1_science_top_1_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 18.0 | 57.5 | 73.2 | 29.8 | 42.3 | 41.8 | 24.1 | 4.7 | 7.2 |
AIME24
- Average Accuracy: 18.00% ± 1.07%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.33% | 7 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 13.33% | 4 | 30 |
| 4 | 20.00% | 6 | 30 |
| 5 | 23.33% | 7 | 30 |
| 6 | 16.67% | 5 | 30 |
| 7 | 13.33% | 4 | 30 |
| 8 | 16.67% | 5 | 30 |
| 9 | 16.67% | 5 | 30 |
| 10 | 16.67% | 5 | 30 |
AMC23
- Average Accuracy: 57.50% ± 1.37%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 62.50% | 25 | 40 |
| 2 | 55.00% | 22 | 40 |
| 3 | 52.50% | 21 | 40 |
| 4 | 60.00% | 24 | 40 |
| 5 | 57.50% | 23 | 40 |
| 6 | 60.00% | 24 | 40 |
| 7 | 55.00% | 22 | 40 |
| 8 | 50.00% | 20 | 40 |
| 9 | 57.50% | 23 | 40 |
| 10 | 65.00% | 26 | 40 |
MATH500
- Accuracy: 73.20%
Accuracy Questions Solved Total Questions 73.20% 366 500
MMLUPro
- Average Accuracy: 29.80% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 29.80% | 149 | 500 |
JEEBench
- Average Accuracy: 42.35% ± 0.07%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 42.28% | 217.75 | 515 |
| 2 | 42.23% | 217.5 | 515 |
| 3 | 42.52% | 219.0 | 515 |
GPQADiamond
- Average Accuracy: 41.75% ± 2.55%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 35.86% | 71 | 198 |
| 2 | 46.46% | 92 | 198 |
| 3 | 42.93% | 85 | 198 |
LiveCodeBench
- Average Accuracy: 24.07% ± 0.79%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 25.44% | 130 | 511 |
| 2 | 22.70% | 116 | 511 |
| 3 | 24.07% | 123 | 511 |
CodeElo
- Average Accuracy: 4.69% ± 0.17%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.86% | 19 | 391 |
| 2 | 4.86% | 19 | 391 |
| 3 | 4.35% | 17 | 391 |
CodeForces
- Average Accuracy: 7.21% ± 0.53%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 7.51% | 34 | 453 |
| 2 | 6.18% | 28 | 453 |
| 3 | 7.95% | 36 | 453 |
- Downloads last month
- 3