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 158k |
|---|---|---|---|---|---|---|
[
{
"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 solve this problem where I have to determine the strongest programmer among N people based on M given comparisons. The strongest is the one who beats everyone else, and there's exactly one such person if possible. Otherwise, output -1.
First, let me understand the problem again. The relations a... |
[
{
"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"
} | **Step 1: Understanding the problem**
We need to calculate the standard molar enthalpy of formation of HgO(s) at 298 K. The given information includes the reaction of 2 mol of Hg(g) with excess O₂ in a fixed-volume bomb calorimeter, leading to HgO(s) formation. The temperature increases from 298.0 K to 312.8 K, and we... |
[
{
"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, let's see. The problem is about maximizing the number of points Kevin can earn by rearranging the array of integers. The rules are that each time he adds a_i to s, if after adding it s becomes even, he divides it by 2 until it's odd. And each operation can only give at most one point. So the goal is to fi... |
[
{
"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 how many of the stars listed would be detectable using ESPRESSO with a 8m VLT telescope, we need to calculate the signal-to-noise ratio (S/N) for each star during a 1-hour exposure and check if it meets or exceeds 10 per binned pixel.
First, let's recall the formula for S/N in spectroscopy. The S/N is giv... |
[{"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, I need to solve this problem where after each operation, I have to find the number o(...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, I need to solve this problem where I have to find the number of incremovable subarra(...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, let's try to figure out this problem. So the problem is about light switches in a bu(...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 after each query (a toggle of a vertex's color), (...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 arranges the dragon parts according to the(...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_code_golf_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 17.7 | 58.0 | 77.0 | 30.6 | 38.8 | 42.6 | 44.4 | 14.4 | 17.2 |
AIME24
- Average Accuracy: 17.67% ± 1.95%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 10.00% | 3 | 30 |
| 2 | 26.67% | 8 | 30 |
| 3 | 30.00% | 9 | 30 |
| 4 | 16.67% | 5 | 30 |
| 5 | 13.33% | 4 | 30 |
| 6 | 10.00% | 3 | 30 |
| 7 | 16.67% | 5 | 30 |
| 8 | 16.67% | 5 | 30 |
| 9 | 16.67% | 5 | 30 |
| 10 | 20.00% | 6 | 30 |
AMC23
- Average Accuracy: 58.00% ± 0.92%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 60.00% | 24 | 40 |
| 2 | 57.50% | 23 | 40 |
| 3 | 55.00% | 22 | 40 |
| 4 | 52.50% | 21 | 40 |
| 5 | 62.50% | 25 | 40 |
| 6 | 57.50% | 23 | 40 |
| 7 | 60.00% | 24 | 40 |
| 8 | 55.00% | 22 | 40 |
| 9 | 60.00% | 24 | 40 |
| 10 | 60.00% | 24 | 40 |
MATH500
- Accuracy: 77.00%
Accuracy Questions Solved Total Questions 77.00% 385 500
MMLUPro
- Average Accuracy: 30.60% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 30.60% | 153 | 500 |
JEEBench
- Average Accuracy: 38.83% ± 0.77%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 36.99% | 190.5 | 515 |
| 2 | 40.05% | 206.25 | 515 |
| 3 | 39.47% | 203.25 | 515 |
GPQADiamond
- Average Accuracy: 42.59% ± 0.60%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 41.41% | 82 | 198 |
| 2 | 42.42% | 84 | 198 |
| 3 | 43.94% | 87 | 198 |
LiveCodeBench
- Average Accuracy: 44.42% ± 1.27%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 45.79% | 234 | 511 |
| 2 | 45.60% | 233 | 511 |
| 3 | 41.88% | 214 | 511 |
CodeElo
- Average Accuracy: 14.41% ± 0.90%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 14.07% | 55 | 391 |
| 2 | 13.04% | 51 | 391 |
| 3 | 16.11% | 63 | 391 |
CodeForces
- Average Accuracy: 17.22% ± 0.80%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.11% | 73 | 453 |
| 2 | 16.78% | 76 | 453 |
| 3 | 18.76% | 85 | 453 |
- Downloads last month
- 4