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
1.94k
292k
[ { "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 carefully. So the problem is about determining the strongest person among N programmers based on M given relations. The strongest person is the one who is stronger than all others. But with the transitivity rule, maybe we can infer some rel...
[ { "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 figure out this problem step by step. So, the question is about calculating the standard molar enthalpy of formation of HgO(s) using the given data from the combustion of Hg(g) in a bomb calorimeter. Hmm, let's start by understanding the reaction and the given information. First, the reactio...
[{"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. I need to solve this problem where Kevin adds up numbers in order and if (...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 by the ESPRESSO (...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 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 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. Hmm, the task is to find the earliest time when all light(...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 process a series of queries on a tree s(...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 generate a Python function that reads N from stdin and outputs a grid wher(...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_openthoughts_3k_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 24.0 59.2 77.2 30.4 39.7 40.2 29.7 5.2 7.6

AIME24

  • Average Accuracy: 24.00% ± 1.69%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 20.00% 6 30
2 20.00% 6 30
3 23.33% 7 30
4 13.33% 4 30
5 26.67% 8 30
6 23.33% 7 30
7 30.00% 9 30
8 33.33% 10 30
9 26.67% 8 30
10 23.33% 7 30

AMC23

  • Average Accuracy: 59.25% ± 1.46%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 52.50% 21 40
2 52.50% 21 40
3 55.00% 22 40
4 62.50% 25 40
5 62.50% 25 40
6 62.50% 25 40
7 55.00% 22 40
8 62.50% 25 40
9 65.00% 26 40
10 62.50% 25 40

MATH500

  • Accuracy: 77.20%
    Accuracy Questions Solved Total Questions
    77.20% 386 500

MMLUPro

  • Average Accuracy: 30.40% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 30.40% 152 500

JEEBench

  • Average Accuracy: 39.66% ± 0.41%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 39.76% 204.75 515
2 38.74% 199.5 515
3 40.49% 208.5 515

GPQADiamond

  • Average Accuracy: 40.24% ± 0.27%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 39.90% 79 198
2 40.91% 81 198
3 39.90% 79 198

LiveCodeBench

  • Average Accuracy: 29.68% ± 0.77%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 30.14% 154 511
2 30.72% 157 511
3 28.18% 144 511

CodeElo

  • Average Accuracy: 5.20% ± 0.31%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 4.60% 18 391
2 5.63% 22 391
3 5.37% 21 391

CodeForces

  • Average Accuracy: 7.58% ± 1.03%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 7.28% 33 453
2 9.49% 43 453
3 5.96% 27 453
Downloads last month
5