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
141
153k
[ { "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, so I need to figure out if there's a unique strongest programmer based on the given information. The problem says there's a transitive relation of superiority, and the strongest person is stronger than everyone else. If there's only one such person, I should print their number; otherwise, print -1. First...
[ { "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 bomb calorimeter experiment where mercury gas is combusted with oxygen to form mercury oxide. Let me try to break down the problem step by step. First, let's write the balanced che...
[{"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>\nAlright, so the problem is about Kevin and his arithmetic skills. His mother has this prob(...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 there's a deck of n cards, and a joker at posi(...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 figure out how many subarrays in a given list are \"inremovable\". Wait(...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 }
"Alright, let's tackle this problem step by step. The problem is about determining the earliest mome(...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 }
"Alright, let's tackle this problem step by step. So, we have a tree with n vertices, each initially(...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>\nAlright, so I need to solve this grid placement problem where Takahashi has to be in the c(...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_all_s1_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 20.7 60.2 77.0 28.8 41.9 41.4 23.2 3.9 5.3

AIME24

  • Average Accuracy: 20.67% ± 2.04%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 30.00% 9 30
2 16.67% 5 30
3 30.00% 9 30
4 16.67% 5 30
5 26.67% 8 30
6 20.00% 6 30
7 13.33% 4 30
8 20.00% 6 30
9 10.00% 3 30
10 23.33% 7 30

AMC23

  • Average Accuracy: 60.25% ± 1.30%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 65.00% 26 40
2 57.50% 23 40
3 57.50% 23 40
4 67.50% 27 40
5 62.50% 25 40
6 60.00% 24 40
7 57.50% 23 40
8 60.00% 24 40
9 52.50% 21 40
10 62.50% 25 40

MATH500

  • Accuracy: 77.00%
    Accuracy Questions Solved Total Questions
    77.00% 385 500

MMLUPro

  • Average Accuracy: 28.80% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 28.80% 144 500

JEEBench

  • Average Accuracy: 41.91% ± 0.54%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 40.58% 209.0 515
2 42.52% 219.0 515
3 42.62% 219.5 515

GPQADiamond

  • Average Accuracy: 41.41% ± 1.09%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 40.91% 81 198
2 39.39% 78 198
3 43.94% 87 198

LiveCodeBench

  • Average Accuracy: 23.22% ± 0.43%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 22.70% 116 511
2 22.90% 117 511
3 24.07% 123 511

CodeElo

  • Average Accuracy: 3.92% ± 0.74%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 2.56% 10 391
2 4.09% 16 391
3 5.12% 20 391

CodeForces

  • Average Accuracy: 5.30% ± 0.34%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 5.74% 26 453
2 4.64% 21 453
3 5.52% 25 453
Downloads last month
5