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 266 162k |
|---|---|---|---|---|---|---|
[
{
"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 figure out if there's a unique strongest programmer based on the given information. The problem is about transitive superiority, meaning if A is stronger than B, and B is stronger than C, then A is stronger than C. The goal is to determine if there's exactly one person who is stronger than ev... |
[
{
"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 combustion reaction in a bomb calorimeter, and I have to use that to calculate the enthalpy of formation. Let me try to break this down step by step.
First, let me recall that the ... |
[
{
"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
} | To solve this problem, we need to determine the maximum number of points Kevin can earn by rearranging the integers \(a_1, a_2, \ldots, a_n\) such that each operation (adding \(a_i\) to \(s\)) results in \(s\) being even, thereby earning a point.
Key steps:
1. **Initialize Counters**: Keep track of the number of even... |
[
{
"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 with an 8m VLT telescope. The key requirement is that the signal-to-noise ratio (S/N) has to be at least 10 per binned pixel during a 1-hour exposure.
First, let me recall some basics about telescopes, sp... |
[
{
"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": 0,
"temperature": 0.7
} | 0 | 321 | CodeForces | {
"expected_answer": "",
"problem_id": "",
"reference_solution": "",
"subject": null,
"type": null
} | To solve the problem of determining the number of distinct positions where the joker can be after each operation, we can model the deck as a series of segments and track how these segments change with each operation. Here's a detailed breakdown of the approach:
1. **Initial Setup**: The joker is initially at position ... |
[{"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 many subarrays in a given list are \"inremovable,\" mean(...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
} | "To solve this problem, we need to determine the earliest moment when all lights in the apartment ar(...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 have this problem where I need to handle a tree with colored vertices (either w(...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 places Takahashi and the dragon parts on a(...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_math_fasttext_pos_numina_neg_natural_reasoning_10k_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 18.3 | 56.5 | 76.8 | 30.0 | 39.0 | 39.9 | 19.6 | 3.6 | 6.8 |
AIME24
- Average Accuracy: 18.33% ± 2.17%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.67% | 5 | 30 |
| 2 | 23.33% | 7 | 30 |
| 3 | 16.67% | 5 | 30 |
| 4 | 30.00% | 9 | 30 |
| 5 | 6.67% | 2 | 30 |
| 6 | 20.00% | 6 | 30 |
| 7 | 13.33% | 4 | 30 |
| 8 | 26.67% | 8 | 30 |
| 9 | 10.00% | 3 | 30 |
| 10 | 20.00% | 6 | 30 |
AMC23
- Average Accuracy: 56.50% ± 1.91%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 47.50% | 19 | 40 |
| 2 | 60.00% | 24 | 40 |
| 3 | 60.00% | 24 | 40 |
| 4 | 50.00% | 20 | 40 |
| 5 | 60.00% | 24 | 40 |
| 6 | 52.50% | 21 | 40 |
| 7 | 47.50% | 19 | 40 |
| 8 | 62.50% | 25 | 40 |
| 9 | 62.50% | 25 | 40 |
| 10 | 62.50% | 25 | 40 |
MATH500
- Accuracy: 76.80%
Accuracy Questions Solved Total Questions 76.80% 384 500
MMLUPro
- Average Accuracy: 30.00% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 30.00% | 150 | 500 |
JEEBench
- Average Accuracy: 38.96% ± 1.17%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 41.50% | 213.75 | 515 |
| 2 | 38.83% | 200.0 | 515 |
| 3 | 36.55% | 188.25 | 515 |
GPQADiamond
- Average Accuracy: 39.90% ± 1.67%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 43.94% | 87 | 198 |
| 2 | 37.37% | 74 | 198 |
| 3 | 38.38% | 76 | 198 |
LiveCodeBench
- Average Accuracy: 19.57% ± 0.49%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 20.16% | 103 | 511 |
| 2 | 18.59% | 95 | 511 |
| 3 | 19.96% | 102 | 511 |
CodeElo
- Average Accuracy: 3.58% ± 0.30%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 3.58% | 14 | 391 |
| 2 | 3.07% | 12 | 391 |
| 3 | 4.09% | 16 | 391 |
CodeForces
- Average Accuracy: 6.84% ± 0.22%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 7.06% | 32 | 453 |
| 2 | 7.06% | 32 | 453 |
| 3 | 6.40% | 29 | 453 |
- Downloads last month
- 7