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
195k
[ { "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 }
To solve this problem, we need to determine if there's a unique strongest programmer based on the given information. The key steps are: 1. **Understand Transitivity**: The relation of being stronger is transitive. So, if person X is stronger than Y, and Y is stronger than Z, then X is stronger than Z. 2. **Check Cons...
[ { "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) with O₂ in a bomb calorimeter. Let me try to break this down step by step. First, the reaction is: Hg(g) + O₂(g) → HgO(s). The problem states that 2 mo...
[ { "content": "You are a coding expert. Given a competition-level coding problem, you need to write a Python program to solve it. You may start by outlining your thought process. In the end, please provide the complete code in a code block enclosed with ``` ```. The code should take stdin as input and print the ...
{ "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> Alright, let me try to figure out this problem. So, the problem is about rearranging the numbers in an array such that when you add each number to a sum 's', if 's' becomes even, you earn a point and keep dividing by 2 until it's odd again. We need to maximize the number of points earned by rearranging the arra...
[ { "content": "Return your final response within \\boxed{} and only include the letter choice (A, B, C, or D) as your final response.\nProblem: How many of the stars listed below would be detectable using the ESPRESSO spectrograph, when it is coupled with one of the 8m VLT telescopes at the Paranal Observatory? ...
{ "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> Okay, so I need to figure out how many of these stars would be detectable by the ESPRESSO spectrograph when used with one of the 8m VLT telescopes at Paranal. The key requirement is that the signal-to-noise ratio (S/N) per binned pixel during a 1-hour exposure has to be at least 10. First, let me recall what ...
[{"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, with a joker at pos(...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 to solve this problem where I have to find the number of(...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, let's tackle this problem. So, we have a grid of size N x N where N is an odd num(...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/b2_math_fasttext_pos_s1k_reformat_neg_lap1official_math_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 19.0 66.8 80.6 30.2 40.9 40.1 21.1 5.0 6.2

AIME24

  • Average Accuracy: 19.00% ± 1.34%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 20.00% 6 30
2 16.67% 5 30
3 23.33% 7 30
4 23.33% 7 30
5 20.00% 6 30
6 23.33% 7 30
7 20.00% 6 30
8 10.00% 3 30
9 13.33% 4 30
10 20.00% 6 30

AMC23

  • Average Accuracy: 66.75% ± 1.73%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 70.00% 28 40
2 75.00% 30 40
3 60.00% 24 40
4 70.00% 28 40
5 62.50% 25 40
6 67.50% 27 40
7 70.00% 28 40
8 62.50% 25 40
9 57.50% 23 40
10 72.50% 29 40

MATH500

  • Accuracy: 80.60%
    Accuracy Questions Solved Total Questions
    80.60% 403 500

MMLUPro

  • Average Accuracy: 30.20% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 30.20% 151 500

JEEBench

  • Average Accuracy: 40.87% ± 0.52%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 40.19% 207.0 515
2 40.29% 207.5 515
3 42.14% 217.0 515

GPQADiamond

  • Average Accuracy: 40.07% ± 0.27%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 40.40% 80 198
2 40.40% 80 198
3 39.39% 78 198

LiveCodeBench

  • Average Accuracy: 21.07% ± 0.75%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 21.72% 111 511
2 19.57% 100 511
3 21.92% 112 511

CodeElo

  • Average Accuracy: 5.03% ± 0.17%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 5.37% 21 391
2 4.86% 19 391
3 4.86% 19 391

CodeForces

  • Average Accuracy: 6.18% ± 0.80%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 6.62% 30 453
2 4.64% 21 453
3 7.28% 33 453
Downloads last month
3