Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
(ReadTimeoutError("HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)"), '(Request ID: c6406e8a-a9c9-40e5-8b3c-10f2e08bf9af)')
Error code: UnexpectedError
Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
context list | gen_kwargs dict | repeat_idx int64 | request_idx int64 | task_name string | metadata dict | model_outputs string |
|---|---|---|---|---|---|---|
[
{
"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 determine_strongest_programmer():
from collections import defaultdict
N, M = map(int, input().split())
relations = [list(map(int, input().split())) for _ in range(M)]
# Create a graph to represent the relations
graph = defaultdict(list)
for A, B in relations:
graph[A].app... |
[
{
"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 figure out the standard molar enthalpy of formation of HgO(s) at 298 K, right? The problem gives me some information about the combustion of Hg(g) in a bomb calorimeter, and I have to calculate the enthalpy change for that reaction. Let me try to break this down step by step.
First, let's wr... |
[
{
"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, so I need to figure out how to maximize the number of points Kevin earns by rearranging the given integers. Let me try to understand the problem step by step.
First, the problem states that Kevin will perform operations for each of the n integers a1, a2, ..., an. Each operation involves adding the curren... |
[
{
"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. The key is that the signal-to-noise ratio (S/N) needs to be at least 10 per binned pixel after a 1-hour exposure.
First, let me recall what factors affect the S/N in astronomy. The ... |
[{"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, so I need to solve this problem where we have a deck of cards with a joker at positi(...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, so I need to figure out how to solve this problem where I have to find the number of(...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 the earliest moment when all the lights in the apartment are(...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 there's a tree with n vertices, each initially(...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
} | "# Generate an executable Python function based on the given problem.\n\ndef arrange_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
} | "<think>\nOkay, so I need to find the probability that a randomly chosen point inside rectangle ABCD(...TRUNCATED) |
End of preview.
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
mlfoundations-dev/a1_math_metamath_aime_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 22.7 | 63.7 | 82.6 | 29.0 | 42.1 | 42.9 | 19.0 | 6.4 | 7.3 |
AIME24
- Average Accuracy: 22.67% ± 2.04%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 20.00% | 6 | 30 |
| 2 | 36.67% | 11 | 30 |
| 3 | 16.67% | 5 | 30 |
| 4 | 23.33% | 7 | 30 |
| 5 | 30.00% | 9 | 30 |
| 6 | 20.00% | 6 | 30 |
| 7 | 13.33% | 4 | 30 |
| 8 | 20.00% | 6 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 26.67% | 8 | 30 |
AMC23
- Average Accuracy: 63.75% ± 1.88%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 67.50% | 27 | 40 |
| 2 | 62.50% | 25 | 40 |
| 3 | 65.00% | 26 | 40 |
| 4 | 57.50% | 23 | 40 |
| 5 | 62.50% | 25 | 40 |
| 6 | 70.00% | 28 | 40 |
| 7 | 62.50% | 25 | 40 |
| 8 | 52.50% | 21 | 40 |
| 9 | 62.50% | 25 | 40 |
| 10 | 75.00% | 30 | 40 |
MATH500
- Accuracy: 82.60%
Accuracy Questions Solved Total Questions 82.60% 413 500
MMLUPro
- Average Accuracy: 29.00% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 29.00% | 145 | 500 |
JEEBench
- Average Accuracy: 42.12% ± 1.36%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 42.14% | 217.0 | 515 |
| 2 | 39.22% | 202.0 | 515 |
| 3 | 45.00% | 231.75 | 515 |
GPQADiamond
- Average Accuracy: 42.93% ± 1.33%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 45.45% | 90 | 198 |
| 2 | 39.90% | 79 | 198 |
| 3 | 43.43% | 86 | 198 |
LiveCodeBench
- Average Accuracy: 19.05% ± 2.38%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 21.33% | 109 | 511 |
| 2 | 14.29% | 73 | 511 |
| 3 | 21.53% | 110 | 511 |
CodeElo
- Average Accuracy: 6.39% ± 0.26%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 6.14% | 24 | 391 |
| 2 | 6.91% | 27 | 391 |
| 3 | 6.14% | 24 | 391 |
CodeForces
- Average Accuracy: 7.28% ± 0.25%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 7.28% | 33 | 453 |
| 2 | 7.73% | 35 | 453 |
| 3 | 6.84% | 31 | 453 |
- Downloads last month
- 6