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 230k |
|---|---|---|---|---|---|---|
[
{
"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 the strongest programmer among N people based on M pieces of information about who is stronger than whom. The key points are that the relations are transitive and there should be exactly one person who is stronger than everyone else. If there's a tie, meaning multiple people could ... |
[
{
"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 the reaction where mercury vapor is combusted with excess oxygen to form mercury oxide. The key data points are the temperature change, the heat capacity of the bomb calorimeter, 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, let's see. I need to help Kevin's mother rearrange the numbers so that Kevin can earn the maximum number of points. The problem is about adding numbers to a sum s and then dividing by 2 until it's odd, earning a point each time s is even. The goal is to maximize the number of points by rearranging the num... |
[
{
"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 the six stars listed would be detectable using the ESPRESSO spectrograph with an 8m VLT telescope. The main criterion is achieving a signal-to-noise ratio (S/N) of at least 10 per binned pixel during a 1-hour exposure.
First, I should recall what factors affect the S/... |
[{"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 problem where we have a deck of cards with(...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 a given list of positive i(...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 time when all the lights in the apartment are o(...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 I have a tree with n vertices, each initially (...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 arranges dragon parts and Takahashi on an (...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>\nTo solve the problem of finding the probability that a randomly chosen point inside rectan(...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_science_stackexchange_physics_1744737192_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 19.7 | 57.5 | 75.6 | 31.0 | 43.9 | 42.6 | 22.7 | 5.3 | 7.6 |
AIME24
- Average Accuracy: 19.67% ± 0.57%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 20.00% | 6 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 20.00% | 6 | 30 |
| 4 | 20.00% | 6 | 30 |
| 5 | 20.00% | 6 | 30 |
| 6 | 16.67% | 5 | 30 |
| 7 | 16.67% | 5 | 30 |
| 8 | 20.00% | 6 | 30 |
| 9 | 23.33% | 7 | 30 |
| 10 | 20.00% | 6 | 30 |
AMC23
- Average Accuracy: 57.50% ± 1.54%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 52.50% | 21 | 40 |
| 2 | 60.00% | 24 | 40 |
| 3 | 62.50% | 25 | 40 |
| 4 | 67.50% | 27 | 40 |
| 5 | 52.50% | 21 | 40 |
| 6 | 52.50% | 21 | 40 |
| 7 | 52.50% | 21 | 40 |
| 8 | 57.50% | 23 | 40 |
| 9 | 60.00% | 24 | 40 |
| 10 | 57.50% | 23 | 40 |
MATH500
- Accuracy: 75.60%
Accuracy Questions Solved Total Questions 75.60% 378 500
MMLUPro
- Average Accuracy: 31.00% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 31.00% | 155 | 500 |
JEEBench
- Average Accuracy: 43.85% ± 0.48%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 43.50% | 224.0 | 515 |
| 2 | 45.00% | 231.75 | 515 |
| 3 | 43.06% | 221.75 | 515 |
GPQADiamond
- Average Accuracy: 42.59% ± 1.37%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 40.91% | 81 | 198 |
| 2 | 40.91% | 81 | 198 |
| 3 | 45.96% | 91 | 198 |
LiveCodeBench
- Average Accuracy: 22.70% ± 1.20%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 24.27% | 124 | 511 |
| 2 | 23.48% | 120 | 511 |
| 3 | 20.35% | 104 | 511 |
CodeElo
- Average Accuracy: 5.29% ± 0.23%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 5.63% | 22 | 391 |
| 2 | 4.86% | 19 | 391 |
| 3 | 5.37% | 21 | 391 |
CodeForces
- Average Accuracy: 7.58% ± 0.60%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 8.39% | 38 | 453 |
| 2 | 7.95% | 36 | 453 |
| 3 | 6.40% | 29 | 453 |
- Downloads last month
- 10