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 904 267k |
|---|---|---|---|---|---|---|
[
{
"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 the given relations. Let's think through this step by step.
First, the problem says that the superiority is a total order, right? Because it's either X is stronger than Y or vice versa, and it's trans... |
[
{
"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>
Alright, so I've got this problem here about calculating the standard molar enthalpy of formation for mercury oxide, HgO(s), using some given data from a bomb calorimeter experiment. Let me see if I can work through this step by step.
First, let me make sure I understand what's being asked. We have 2 moles of ... |
[
{
"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 rearrange the given integers so that Kevin earns the maximum number of points. The rules are a bit specific. Let me try to understand what's required here.
So, for each operation, Kevin adds a_i to s. If the sum becomes even, he earns a point and keeps dividing by 2 until it'... |
[
{
"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>
Alright, I need to figure out how many of these stars would be detectable using the ESPRESSO spectrograph with an 8m VLT telescope at Paranal. The main criterion is that the signal-to-noise ratio (S/N) per binned pixel has to be at least 10 during a 1-hour exposure.
First, I should recall what S/N means. It'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, I need to solve this problem where after each operation, I have to find the number o(...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 number of incremovable subarra(...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 try to figure out this problem. So, the task is to find the earliest time when(...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 after each toggle query, I have to check if all t(...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, let's see. I need to generate a grid where Takahashi is placed at the center, and al(...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/fig1_scaling_bespoke_stratos_10k_eval_636d
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AMC23 | MATH500 | MMLUPro | JEEBench | GPQADiamond | LiveCodeBench | CodeElo | CodeForces |
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | 18.7 | 61.0 | 77.6 | 28.2 | 40.2 | 38.2 | 33.9 | 8.3 | 12.5 |
AIME24
- Average Accuracy: 18.67% ± 1.35%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 13.33% | 4 | 30 |
| 2 | 20.00% | 6 | 30 |
| 3 | 13.33% | 4 | 30 |
| 4 | 20.00% | 6 | 30 |
| 5 | 13.33% | 4 | 30 |
| 6 | 20.00% | 6 | 30 |
| 7 | 23.33% | 7 | 30 |
| 8 | 20.00% | 6 | 30 |
| 9 | 16.67% | 5 | 30 |
| 10 | 26.67% | 8 | 30 |
AMC23
- Average Accuracy: 61.00% ± 1.47%
- Number of Runs: 10
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 60.00% | 24 | 40 |
| 2 | 55.00% | 22 | 40 |
| 3 | 67.50% | 27 | 40 |
| 4 | 55.00% | 22 | 40 |
| 5 | 57.50% | 23 | 40 |
| 6 | 57.50% | 23 | 40 |
| 7 | 65.00% | 26 | 40 |
| 8 | 65.00% | 26 | 40 |
| 9 | 67.50% | 27 | 40 |
| 10 | 60.00% | 24 | 40 |
MATH500
- Accuracy: 77.60%
Accuracy Questions Solved Total Questions 77.60% 388 500
MMLUPro
- Average Accuracy: 28.20% ± 0.00%
- Number of Runs: 1
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 28.20% | 141 | 500 |
JEEBench
- Average Accuracy: 40.16% ± 0.38%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 39.32% | 202.5 | 515 |
| 2 | 40.24% | 207.25 | 515 |
| 3 | 40.92% | 210.75 | 515 |
GPQADiamond
- Average Accuracy: 38.22% ± 0.36%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 38.38% | 76 | 198 |
| 2 | 38.89% | 77 | 198 |
| 3 | 37.37% | 74 | 198 |
LiveCodeBench
- Average Accuracy: 33.86% ± 0.97%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 34.05% | 174 | 511 |
| 2 | 32.09% | 164 | 511 |
| 3 | 35.42% | 181 | 511 |
CodeElo
- Average Accuracy: 8.27% ± 0.45%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 7.42% | 29 | 391 |
| 2 | 8.44% | 33 | 391 |
| 3 | 8.95% | 35 | 391 |
CodeForces
- Average Accuracy: 12.51% ± 0.27%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 12.14% | 55 | 453 |
| 2 | 12.36% | 56 | 453 |
| 3 | 13.02% | 59 | 453 |
- Downloads last month
- 3