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
854k
[ { "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 programming problem. Let's read the problem statement carefully. So the task is to determine the strongest programmer among N people based on given M relations. The relations are pairs (A_i, B_i) meaning A_i is stronger than B_i. The superiority is transitive, so if A > B and B > C, ...
[ { "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 a reaction where 2 moles of Hg(g) are combusted in a bomb calorimeter with excess O2, resulting in HgO(s). The temperature increased from 298.0 K to 312.8 K, and the heat capacity of ...
[{"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": 1, "temperature": 0.7 }
1
363
CodeForces
{ "expected_answer": "", "problem_id": "", "reference_solution": "", "subject": null, "type": null }
"<think>\nOkay, let's see. The problem is to maximize the number of points Kevin can earn by rearran(...TRUNCATED)
[{"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, so I need to figure out how many of these stars would be detectable using the ESPRES(...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, so I need to solve this problem where I have a deck of cards with a joker at positio(...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 solve this problem where I have to find the total number of incremovabl(...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 solve this programming problem where we have to determine the earliest (...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 vertices colored white or b(...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 solves this problem. Let's read the proble(...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 geometry problem where I have a rectangle ABCD with center O(...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_globalbatchsize96_lr2e5_epochs11_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 12.7 50.0 71.0 27.4 34.6 27.9 19.6 4.3 4.4

AIME24

  • Average Accuracy: 12.67% ± 1.14%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 13.33% 4 30
2 16.67% 5 30
3 13.33% 4 30
4 13.33% 4 30
5 6.67% 2 30
6 10.00% 3 30
7 13.33% 4 30
8 20.00% 6 30
9 10.00% 3 30
10 10.00% 3 30

AMC23

  • Average Accuracy: 50.00% ± 1.87%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 52.50% 21 40
2 47.50% 19 40
3 60.00% 24 40
4 50.00% 20 40
5 52.50% 21 40
6 55.00% 22 40
7 40.00% 16 40
8 45.00% 18 40
9 55.00% 22 40
10 42.50% 17 40

MATH500

  • Accuracy: 71.00%
    Accuracy Questions Solved Total Questions
    71.00% 355 500

MMLUPro

  • Average Accuracy: 27.40% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 27.40% 137 500

JEEBench

  • Average Accuracy: 34.58% ± 0.85%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 34.51% 177.75 515
2 32.82% 169.0 515
3 36.41% 187.5 515

GPQADiamond

  • Average Accuracy: 27.95% ± 1.91%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 28.28% 56 198
2 31.82% 63 198
3 23.74% 47 198

LiveCodeBench

  • Average Accuracy: 19.63% ± 0.75%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 18.79% 96 511
2 21.14% 108 511
3 18.98% 97 511

CodeElo

  • Average Accuracy: 4.26% ± 0.47%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 4.60% 18 391
2 3.32% 13 391
3 4.86% 19 391

CodeForces

  • Average Accuracy: 4.42% ± 0.22%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 4.19% 19 453
2 4.86% 22 453
3 4.19% 19 453
Downloads last month
3