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 208 170k |
|---|---|---|---|---|---|---|
[
{
"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 who the strongest programmer is among N people based on some given information. The problem says that each pair of programmers has a relation where one is stronger than the other, and this relation is transitive. That means if A is stronger than B, and B is stronger than C, then 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"
} | <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 of Hg(g) in a bomb calorimeter, and I have to use that to calculate the enthalpy of formation of HgO(s). Let me break down the problem step by step.
First, 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
} | <think>
Okay, so I need to help Kevin maximize the number of points he can earn by rearranging the given integers. Let me try to understand the problem step by step.
First, the problem says that for each integer in the list, we add it to a running total called `s`. If `s` becomes even after adding the current integer,... |
[
{
"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 8-meter VLT telescope. The key requirement is that the signal-to-noise ratio (S/N) needs to be at least 10 per binned pixel after a 1-hour exposure. Hmm, let me start by recalling what factors affec... |
[{"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 many subarrays in a given list are \"incremovable\". Hmm(...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 a problem where I have a tree with vertices colored either white (...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 a dragon on an N x 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_math_fasttext_pos_numina_neg_natural_reasoning_0.3k_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 14.7 | 51.5 | 72.4 | 27.6 | 36.1 | 36.2 | 21.0 | 2.9 | 4.9 |
AIME24
- Average Accuracy: 14.67% ± 1.07%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 16.67% | 5 | 30 |
| 2 | 13.33% | 4 | 30 |
| 3 | 16.67% | 5 | 30 |
| 4 | 20.00% | 6 | 30 |
| 5 | 16.67% | 5 | 30 |
| 6 | 10.00% | 3 | 30 |
| 7 | 16.67% | 5 | 30 |
| 8 | 10.00% | 3 | 30 |
| 9 | 10.00% | 3 | 30 |
| 10 | 16.67% | 5 | 30 |
AMC23
- Average Accuracy: 51.50% ± 1.74%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 60.00% | 24 | 40 |
| 2 | 55.00% | 22 | 40 |
| 3 | 50.00% | 20 | 40 |
| 4 | 47.50% | 19 | 40 |
| 5 | 57.50% | 23 | 40 |
| 6 | 47.50% | 19 | 40 |
| 7 | 55.00% | 22 | 40 |
| 8 | 40.00% | 16 | 40 |
| 9 | 52.50% | 21 | 40 |
| 10 | 50.00% | 20 | 40 |
MATH500
- Accuracy: 72.40%
Accuracy Questions Solved Total Questions 72.40% 362 500
MMLUPro
- Average Accuracy: 27.60% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 27.60% | 138 | 500 |
JEEBench
- Average Accuracy: 36.08% ± 0.85%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 35.10% | 180.75 | 515 |
| 2 | 38.16% | 196.5 | 515 |
| 3 | 35.00% | 180.25 | 515 |
GPQADiamond
- Average Accuracy: 36.20% ± 0.60%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 34.85% | 69 | 198 |
| 2 | 37.37% | 74 | 198 |
| 3 | 36.36% | 72 | 198 |
LiveCodeBench
- Average Accuracy: 21.00% ± 0.26%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 20.74% | 106 | 511 |
| 2 | 20.74% | 106 | 511 |
| 3 | 21.53% | 110 | 511 |
CodeElo
- Average Accuracy: 2.90% ± 0.31%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 2.30% | 9 | 391 |
| 2 | 3.07% | 12 | 391 |
| 3 | 3.32% | 13 | 391 |
CodeForces
- Average Accuracy: 4.86% ± 0.46%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 4.19% | 19 | 453 |
| 2 | 4.64% | 21 | 453 |
| 3 | 5.74% | 26 | 453 |
- Downloads last month
- 7