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 9 168k |
|---|---|---|---|---|---|---|
[
{
"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, so I need to write a Python function that determines the strongest programmer among N people based on M pieces of information about their superiority. The function should take input from stdin and print the result. Let me break down the problem step by step.
First, the input format: the first line gives ... |
[
{
"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 reaction where 2 moles of Hg(g) are combusted in a bomb calorimeter with excess O2, leading to HgO(s) formation. The temperature increases from 298 K to 312.8 K, and I have the heat... |
[
{
"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 help Kevin maximize his points by rearranging the numbers. Let me try to understand the problem first.
From what I can tell, Kevin is adding numbers to a running total `s`, starting from 0. If the sum becomes even, he earns a point and keeps dividing by 2 until it's odd again. The goal is t... |
[{"content":"Return your final response within \\boxed{} and only include the letter choice (A, B, C(...TRUNCATED) | {
"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>\nOkay, so I need to figure out how many of the given stars would be detectable using the ES(...TRUNCATED) |
[{"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 figure out how to solve this card manipulation problem where a joker's (...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
} | "To solve this problem, we need to determine the number of subarrays that, when removed from the giv(...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 \"Chain Queries\" problem. Let me read the description again(...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
} | "```python\ndef place_takahashi_and_dragon():\n import sys\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
} | "<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/b2_science_fasttext_pos_scp116k_0.3k_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 15.0 | 51.2 | 73.4 | 26.0 | 38.1 | 34.0 | 19.4 | 4.3 | 6.1 |
AIME24
- Average Accuracy: 15.00% ± 1.18%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 10.00% | 3 | 30 |
| 2 | 13.33% | 4 | 30 |
| 3 | 13.33% | 4 | 30 |
| 4 | 16.67% | 5 | 30 |
| 5 | 13.33% | 4 | 30 |
| 6 | 23.33% | 7 | 30 |
| 7 | 16.67% | 5 | 30 |
| 8 | 10.00% | 3 | 30 |
| 9 | 16.67% | 5 | 30 |
| 10 | 16.67% | 5 | 30 |
AMC23
- Average Accuracy: 51.25% ± 1.94%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 60.00% | 24 | 40 |
| 2 | 47.50% | 19 | 40 |
| 3 | 47.50% | 19 | 40 |
| 4 | 47.50% | 19 | 40 |
| 5 | 40.00% | 16 | 40 |
| 6 | 52.50% | 21 | 40 |
| 7 | 52.50% | 21 | 40 |
| 8 | 52.50% | 21 | 40 |
| 9 | 50.00% | 20 | 40 |
| 10 | 62.50% | 25 | 40 |
MATH500
- Accuracy: 73.40%
Accuracy Questions Solved Total Questions 73.40% 367 500
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: 38.09% ± 0.96%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 37.33% | 192.25 | 515 |
| 2 | 36.55% | 188.25 | 515 |
| 3 | 40.39% | 208.0 | 515 |
GPQADiamond
- Average Accuracy: 34.01% ± 1.35%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 34.85% | 69 | 198 |
| 2 | 30.81% | 61 | 198 |
| 3 | 36.36% | 72 | 198 |
LiveCodeBench
- Average Accuracy: 19.37% ± 1.67%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 21.33% | 109 | 511 |
| 2 | 16.05% | 82 | 511 |
| 3 | 20.74% | 106 | 511 |
CodeElo
- Average Accuracy: 4.26% ± 0.56%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 3.58% | 14 | 391 |
| 2 | 5.37% | 21 | 391 |
| 3 | 3.84% | 15 | 391 |
CodeForces
- Average Accuracy: 6.11% ± 0.27%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 5.74% | 26 | 453 |
| 2 | 5.96% | 27 | 453 |
| 3 | 6.62% | 30 | 453 |
- Downloads last month
- 3