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 8 868k |
|---|---|---|---|---|---|---|
[
{
"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 if there's a unique strongest programmer based on given superiority relations. Hmm. Let's read the problem carefully.
So, the problem is about finding the strongest person in a group where everyone has a strict ranking. The relations are transitive, ... |
[
{
"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, let's try to solve this problem step by step. So, we need to find the standard molar enthalpy of formation of HgO(s) at 298 K. The problem gives us the information about the combustion of Hg(g) in a bomb calorimeter, leading to HgO(s). The key steps here are to write the balanced equation, calculate the h... |
[
{
"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 to find the maximum number of points Kevin can earn by rearranging the array. Wait, the key here is that each time he adds an element to the sum, and if the sum becomes even, he can divide it by 2 repeatedly until it's odd. Each time he does that, he earns a point. But he can ear... |
[
{
"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
} | \boxed{C} |
[{"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 coding problem. Let's read the problem statement carefully.\n\n(...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 total number of incremovable s(...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 tackle this problem step by step. So, the task is to determine the earliest ti(...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 we have a tree and we need to toggle colors of ve(...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 solve this problem. Let's read the problem carefully. The task is to place(...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 solve this problem: Rectangle ABCD has center O, and the ratio of AB to(...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/316_globalbatchsize64_lr1e5_epochs11_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 13.0 | 53.5 | 73.4 | 23.8 | 37.6 | 29.3 | 20.0 | 3.2 | 3.5 |
AIME24
- Average Accuracy: 13.00% ± 1.37%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 6.67% | 2 | 30 |
| 2 | 10.00% | 3 | 30 |
| 3 | 6.67% | 2 | 30 |
| 4 | 13.33% | 4 | 30 |
| 5 | 16.67% | 5 | 30 |
| 6 | 10.00% | 3 | 30 |
| 7 | 13.33% | 4 | 30 |
| 8 | 16.67% | 5 | 30 |
| 9 | 20.00% | 6 | 30 |
| 10 | 16.67% | 5 | 30 |
AMC23
- Average Accuracy: 53.50% ± 0.88%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 57.50% | 23 | 40 |
| 2 | 55.00% | 22 | 40 |
| 3 | 55.00% | 22 | 40 |
| 4 | 55.00% | 22 | 40 |
| 5 | 52.50% | 21 | 40 |
| 6 | 52.50% | 21 | 40 |
| 7 | 50.00% | 20 | 40 |
| 8 | 57.50% | 23 | 40 |
| 9 | 50.00% | 20 | 40 |
| 10 | 50.00% | 20 | 40 |
MATH500
- Accuracy: 73.40%
Accuracy Questions Solved Total Questions 73.40% 367 500
MMLUPro
- Average Accuracy: 23.80% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.80% | 119 | 500 |
JEEBench
- Average Accuracy: 37.56% ± 0.42%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 36.75% | 189.25 | 515 |
| 2 | 37.43% | 192.75 | 515 |
| 3 | 38.50% | 198.25 | 515 |
GPQADiamond
- Average Accuracy: 29.29% ± 4.23%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 22.22% | 44 | 198 |
| 2 | 26.26% | 52 | 198 |
| 3 | 39.39% | 78 | 198 |
LiveCodeBench
- Average Accuracy: 20.03% ± 0.17%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 19.77% | 101 | 511 |
| 2 | 20.35% | 104 | 511 |
| 3 | 19.96% | 102 | 511 |
CodeElo
- Average Accuracy: 3.15% ± 0.47%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 2.81% | 11 | 391 |
| 2 | 2.56% | 10 | 391 |
| 3 | 4.09% | 16 | 391 |
CodeForces
- Average Accuracy: 3.46% ± 0.27%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 3.09% | 14 | 453 |
| 2 | 3.31% | 15 | 453 |
| 3 | 3.97% | 18 | 453 |
- Downloads last month
- 3