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
1.89k
252k
[ { "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 who the strongest programmer is among N people based on M pieces of information about their superiority. The problem says that if person X is stronger than person Y and person Y is stronger than person Z, then person X is stronger than person Z. So, the superiority is transitive. T...
[ { "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 combustion reaction of Hg(g) in a bomb calorimeter, and I have to use that to calculate the enthalpy of formation of HgO. Let me break down the problem step by step. First, the rea...
[{"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, so I need to help Kevin's mom figure out how to rearrange the numbers so that Kevin (...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 figure out where the joker can be after each operation in a deck of car(...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 of numbers are \"incremov(...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 figure out when all the lights in an apartment will be turned on. The a(...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 have this problem where I need to handle a tree with vertices colored either wh(...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 figure out how to arrange the dragon parts and Takahashi on an N x N gr(...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 figure out the probability that a randomly chosen point inside rectangl(...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/b2_math_fasttext_pos_numina_neg_natural_reasoning_1k_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 15.0 55.5 74.0 27.4 36.5 34.8 19.2 3.2 3.6

AIME24

  • Average Accuracy: 15.00% ± 1.27%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 13.33% 4 30
2 10.00% 3 30
3 20.00% 6 30
4 16.67% 5 30
5 16.67% 5 30
6 13.33% 4 30
7 10.00% 3 30
8 20.00% 6 30
9 20.00% 6 30
10 10.00% 3 30

AMC23

  • Average Accuracy: 55.50% ± 1.57%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 55.00% 22 40
2 50.00% 20 40
3 52.50% 21 40
4 60.00% 24 40
5 52.50% 21 40
6 62.50% 25 40
7 52.50% 21 40
8 55.00% 22 40
9 50.00% 20 40
10 65.00% 26 40

MATH500

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

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: 36.46% ± 0.64%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 37.57% 193.5 515
2 34.95% 180.0 515
3 36.84% 189.75 515

GPQADiamond

  • Average Accuracy: 34.85% ± 0.00%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 34.85% 69 198
2 34.85% 69 198
3 34.85% 69 198

LiveCodeBench

  • Average Accuracy: 19.24% ± 0.62%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 19.18% 98 511
2 20.35% 104 511
3 18.20% 93 511

CodeElo

  • Average Accuracy: 3.24% ± 0.81%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 1.79% 7 391
2 4.60% 18 391
3 3.32% 13 391

CodeForces

  • Average Accuracy: 3.61% ± 1.08%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 2.21% 10 453
2 2.87% 13 453
3 5.74% 26 453
Downloads last month
4