Dataset Viewer
Auto-converted to Parquet Duplicate
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
9
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 find the strongest programmer among N people based on M relations of superiority. The superiority is transitive, so if A is stronger than B, and B is stronger than C, then A is stronger than C. The output should be the strongest person's number if there's exact...
[ { "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 tackle this problem step by step. So, we have to calculate the standard molar enthalpy of formation of HgO(s) at 298 K. The reaction is the combustion of Hg(g) in a fixed volume bomb calorimeter with excess O₂, forming HgO(s). The temperature increases from 298.0 K to 312.8 K, and we need to conside...
[ { "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 solve this problem where given a list of numbers, we have to rearrange them in a way that maximizes the number of points Kevin earns. The way points are earned is by adding each number in order, and if the sum becomes even, he divides it by 2 repeatedly until it's odd and earns a poin...
[{"content":"Return your final response within \\boxed{} and only include the letter choice (A, B, C(...TRUNCATED)
{ "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>\nOkay, let's try to figure out which stars would be detectable with the ESPRESSO spectrogra(...TRUNCATED)
[{"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 determine the num(...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, let's tackle this problem step by step. So, the task is to find all the incremovable(...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. Hmm, the problem is about finding 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 I have to determine if after each query, all the (...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 th(...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: Given a rectangle ABCD with center O, and the ratio(...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_globalbatchsize32_lr2e5_epochs11_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 15.0 53.8 74.4 25.8 41.1 37.2 25.4 6.1 8.4

AIME24

  • Average Accuracy: 15.00% ± 1.51%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 13.33% 4 30
2 23.33% 7 30
3 16.67% 5 30
4 16.67% 5 30
5 6.67% 2 30
6 16.67% 5 30
7 16.67% 5 30
8 20.00% 6 30
9 10.00% 3 30
10 10.00% 3 30

AMC23

  • Average Accuracy: 53.75% ± 1.67%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 47.50% 19 40
2 57.50% 23 40
3 55.00% 22 40
4 55.00% 22 40
5 42.50% 17 40
6 55.00% 22 40
7 57.50% 23 40
8 52.50% 21 40
9 62.50% 25 40
10 52.50% 21 40

MATH500

  • Accuracy: 74.40%
    Accuracy Questions Solved Total Questions
    74.40% 372 500

MMLUPro

  • Average Accuracy: 25.80% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 25.80% 129 500

JEEBench

  • Average Accuracy: 41.12% ± 1.14%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 38.35% 197.5 515
2 42.77% 220.25 515
3 42.23% 217.5 515

GPQADiamond

  • Average Accuracy: 37.21% ± 0.55%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 37.88% 75 198
2 37.88% 75 198
3 35.86% 71 198

LiveCodeBench

  • Average Accuracy: 25.44% ± 0.81%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 26.61% 136 511
2 23.87% 122 511
3 25.83% 132 511

CodeElo

  • Average Accuracy: 6.14% ± 0.26%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 6.39% 25 391
2 5.63% 22 391
3 6.39% 25 391

CodeForces

  • Average Accuracy: 8.39% ± 0.34%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 8.61% 39 453
2 7.73% 35 453
3 8.83% 40 453
Downloads last month
6