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
1.36k
732k
[ { "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, let's try to figure out how to solve this problem. So, we need to determine if there's a unique strongest programmer based on the given superiority relations. The key points here are transitivity and that each pair has exactly one direction of superiority. First, the problem states that the superiority ...
[ { "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, given some experimental data from a combustion reaction in a bomb calorimeter. Let me try to break this down step by step. First, the problem states that 2 moles of Hg(g) are combusted in a fixed volume bomb calorimeter with ...
[{"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 numbers in order and earns (...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 listed in the problem would be detec(...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, let's try to figure out how to solve this problem. So, we have a deck of cards with (...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 try to figure out how to solve this problem. So, the task is to find the numbe(...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 try to figure out how to solve this problem. So, the problem is about light sw(...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 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>\nOkay, let's see. I need to create a Python function that generates a grid with N rows and (...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/a1_math_tiger_lab_math_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 20.3 57.5 74.0 29.4 38.1 43.4 24.2 5.3 7.7

AIME24

  • Average Accuracy: 20.33% ± 1.10%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 16.67% 5 30
2 23.33% 7 30
3 20.00% 6 30
4 26.67% 8 30
5 23.33% 7 30
6 20.00% 6 30
7 16.67% 5 30
8 16.67% 5 30
9 16.67% 5 30
10 23.33% 7 30

AMC23

  • Average Accuracy: 57.50% ± 1.17%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 52.50% 21 40
2 57.50% 23 40
3 65.00% 26 40
4 57.50% 23 40
5 55.00% 22 40
6 52.50% 21 40
7 62.50% 25 40
8 57.50% 23 40
9 57.50% 23 40
10 57.50% 23 40

MATH500

  • Accuracy: 74.00%
    Accuracy Questions Solved Total Questions
    74.00% 370 500

MMLUPro

  • Average Accuracy: 29.40% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 29.40% 147 500

JEEBench

  • Average Accuracy: 38.11% ± 0.12%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 38.40% 197.75 515
2 37.91% 195.25 515
3 38.01% 195.75 515

GPQADiamond

  • Average Accuracy: 43.43% ± 2.12%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 44.95% 89 198
2 38.38% 76 198
3 46.97% 93 198

LiveCodeBench

  • Average Accuracy: 24.20% ± 1.77%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 25.24% 129 511
2 26.61% 136 511
3 20.74% 106 511

CodeElo

  • Average Accuracy: 5.29% ± 0.60%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 6.39% 25 391
2 5.12% 20 391
3 4.35% 17 391

CodeForces

  • Average Accuracy: 7.65% ± 0.37%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 7.28% 33 453
2 8.39% 38 453
3 7.28% 33 453
Downloads last month
3