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 123k |
|---|---|---|---|---|---|---|
[
{
"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_programmer(N, M, relations):
graph = defaultdict(list)
for a, b in relations:
graph[a].append(b)
def is_strongest(person):
for next_person in graph[person]:
if not is_transitive(person, next_person):
return ... |
[
{
"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: 2 moles of Hg(g) are combusted in a bomb calorimeter with excess O2, forming HgO(s). The temperature increases from 298.0 K to 312.8 K. The heat capacity of the bomb calorimeter is 20.00 k... |
[
{
"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>
Alright, let me try to figure out this problem. So, the problem is about maximizing the number of points Kevin can earn by rearranging the given integers. The key operations are adding each integer to a sum 's' and if the sum becomes even, Kevin earns a point and keeps dividing by 2 until it's odd again. The go... |
[
{
"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 six stars would be detectable using the ESPRESSO spectrograph on the VLT telescopes at Paranal. 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. Let me recall what factors influence the S/N in astron... |
[{"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 n cards with a joker at posi(...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 count all the subarrays in the given list `nums` that(...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 we have a tree of n vertices, each initially c(...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
} | "To solve this problem, we need to place Takahashi and the dragon parts on an N x N grid such that t(...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. 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_math_formulas_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 21.3 | 61.3 | 79.0 | 29.8 | 37.1 | 41.8 | 18.0 | 6.3 | 6.5 |
AIME24
- Average Accuracy: 21.33% ± 1.65%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.33% | 7 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 26.67% | 8 | 30 |
| 4 | 26.67% | 8 | 30 |
| 5 | 13.33% | 4 | 30 |
| 6 | 30.00% | 9 | 30 |
| 7 | 20.00% | 6 | 30 |
| 8 | 13.33% | 4 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 20.00% | 6 | 30 |
AMC23
- Average Accuracy: 61.25% ± 1.13%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 62.50% | 25 | 40 |
| 2 | 55.00% | 22 | 40 |
| 3 | 60.00% | 24 | 40 |
| 4 | 57.50% | 23 | 40 |
| 5 | 67.50% | 27 | 40 |
| 6 | 65.00% | 26 | 40 |
| 7 | 62.50% | 25 | 40 |
| 8 | 57.50% | 23 | 40 |
| 9 | 62.50% | 25 | 40 |
| 10 | 62.50% | 25 | 40 |
MATH500
- Accuracy: 79.00%
Accuracy Questions Solved Total Questions 79.00% 395 500
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: 37.07% ± 0.66%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 36.65% | 188.75 | 515 |
| 2 | 35.92% | 185.0 | 515 |
| 3 | 38.64% | 199.0 | 515 |
GPQADiamond
- Average Accuracy: 41.75% ± 0.50%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 42.93% | 85 | 198 |
| 2 | 40.91% | 81 | 198 |
| 3 | 41.41% | 82 | 198 |
LiveCodeBench
- Average Accuracy: 18.00% ± 1.33%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 19.96% | 102 | 511 |
| 2 | 18.59% | 95 | 511 |
| 3 | 15.46% | 79 | 511 |
CodeElo
- Average Accuracy: 6.31% ± 0.34%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 6.65% | 26 | 391 |
| 2 | 6.65% | 26 | 391 |
| 3 | 5.63% | 22 | 391 |
CodeForces
- Average Accuracy: 6.55% ± 0.39%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 5.96% | 27 | 453 |
| 2 | 6.40% | 29 | 453 |
| 3 | 7.28% | 33 | 453 |
- Downloads last month
- 45