context listlengths 1 1 | gen_kwargs dict | repeat_idx int64 0 4 | request_idx int64 0 510 | task_name stringclasses 6
values | metadata dict | model_outputs stringlengths 1.42k 151k |
|---|---|---|---|---|---|---|
[
{
"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 three cards with letters $\\texttt{a}$, $\\texttt{b}$, $\\texttt{c}$ placed in a row in some order. You can ... | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 0 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": ""
} | <|begin_of_thought|>
Okay, let's see. The problem is about checking if a given permutation of the three letters a, b, c can be turned into "abc" with at most one swap. So, for each test case, which is a string of three distinct characters a, b, c, we need to determine if it's possible.
Hmm. So first, the initial thou... |
[
{
"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.Slavic is preparing a present for a friend's birthday. He has an array $a$ of $n$ digits and the present will be the p... | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 1 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": ""
} | <|begin_of_thought|>
Okay, let's see. The problem is about finding the maximum product of digits after adding 1 to exactly one digit. Hmm. So, the input is an array of digits, and we have to choose which one to increment by 1 to get the largest possible product.
First, I need to understand the approach here. For eac... |
[
{
"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.You are given a strip of paper $s$ that is $n$ cells long. Each cell is either black or white. In an operation you can... | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 2 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": ""
} | <|begin_of_thought|>
Okay, let's see. I need to find the minimum number of operations to turn all the black cells into white. Each operation can take any k consecutive cells and turn them all white. So the problem is about covering all the B's with as few k-length intervals as possible, right?
Hmm. Let's think about ... |
[
{
"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.You are given a string $s$ of length $n$, consisting of lowercase Latin letters, and an integer $k$.\n\nYou need to ch... | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 3 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": ""
} | <|begin_of_thought|>
Okay, let's see. I need to solve this problem where I have to determine if after removing exactly k characters from a string, the remaining characters can be rearranged into a palindrome. Hmm. So the main idea is to check the conditions for forming a palindrome with the remaining characters.
Firs... |
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 4 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": ""
} | "<|begin_of_thought|>\n\nOkay, let's see. I need to find the minimum number of operations to make th(...TRUNCATED) |
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 5 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": ""
} | "<|begin_of_thought|>\n\nOkay, let's try to figure out this problem. So the problem is about a game (...TRUNCATED) |
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 6 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": ""
} | "<|begin_of_thought|>\n\nOkay, let's try to understand this problem. So, the task is to find for eac(...TRUNCATED) |
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 7 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": ""
} | "<|begin_of_thought|>\n\nOkay, let's see. I need to find the maximum sum of a non-empty subarray whe(...TRUNCATED) |
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 8 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": ""
} | "<|begin_of_thought|>\n\nOkay, let's try to solve this problem. Hmm, the problem is about counting p(...TRUNCATED) |
[{"content":"Generate an executable Python function generated from the given prompt. Return the func(...TRUNCATED) | {
"do_sample": false,
"max_new_tokens": 32768,
"seed": 0,
"temperature": 0.7
} | 0 | 9 | LiveCodeBench | {
"expected_answer": "",
"problem_id": "",
"reference_solution": ""
} | "<|begin_of_thought|>\n\nOkay, let's see. I need to write a Python function that counts how many pas(...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/OpenThinker-32B_1743569343_eval_0981
Precomputed model outputs for evaluation.
Evaluation Results
Summary
| Metric | AIME24 | AIME25 | AMC23 | MATH500 | GPQADiamond | LiveCodeBench |
|---|---|---|---|---|---|---|
| Accuracy | 67.3 | 52.7 | 93.5 | 90.4 | 22.9 | 69.5 |
AIME24
- Average Accuracy: 67.33% ± 2.56%
- Number of Runs: 5
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 63.33% | 19 | 30 |
| 2 | 70.00% | 21 | 30 |
| 3 | 60.00% | 18 | 30 |
| 4 | 66.67% | 20 | 30 |
| 5 | 76.67% | 23 | 30 |
AIME25
- Average Accuracy: 52.67% ± 2.19%
- Number of Runs: 5
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 46.67% | 14 | 30 |
| 2 | 56.67% | 17 | 30 |
| 3 | 46.67% | 14 | 30 |
| 4 | 56.67% | 17 | 30 |
| 5 | 56.67% | 17 | 30 |
AMC23
- Average Accuracy: 93.50% ± 2.07%
- Number of Runs: 5
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 87.50% | 35 | 40 |
| 2 | 92.50% | 37 | 40 |
| 3 | 97.50% | 39 | 40 |
| 4 | 100.00% | 40 | 40 |
| 5 | 90.00% | 36 | 40 |
MATH500
- Accuracy: 90.40%
Accuracy Questions Solved Total Questions 90.40% 452 500
GPQADiamond
- Average Accuracy: 22.90% ± 0.69%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 23.74% | 47 | 198 |
| 2 | 21.21% | 42 | 198 |
| 3 | 23.74% | 47 | 198 |
LiveCodeBench
- Average Accuracy: 69.47% ± 0.34%
- Number of Runs: 3
| Run | Accuracy | Questions Solved | Total Questions |
|---|---|---|---|
| 1 | 70.06% | 358 | 511 |
| 2 | 68.88% | 352 | 511 |
| 3 | 69.47% | 355 | 511 |
- Downloads last month
- 5