Dataset Viewer
Auto-converted to Parquet Duplicate
Search is not available for this dataset
context
list
gen_kwargs
dict
repeat_idx
int64
request_idx
int64
task_name
string
metadata
dict
model_outputs
string
[ { "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 superiority relations. The key points are: 1. **Transitivity**: If person A is stronger than B, and B is stronger than C, then A is stronger than C. 2. **Consistency**: All given relations must be consistent with th...
[ { "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" }
To solve this problem, we need to determine the standard molar enthalpy of formation of HgO(s) at 298 K. We can approach this by using the given information and applying thermodynamic principles. ### Step-by-Step Solution: 1. **Write the balanced chemical equation for the reaction:** \[ \mathrm{Hg}(g) + \frac{1...
[ { "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> Okay, let's see. The problem is about maximizing the number of points Kevin can get by rearranging the array. The points are earned when adding a number to s makes it even, and then after division, s becomes odd. So each time we add an even number, especially if we can arrange it such that after adding it, s be...
[ { "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 }
To determine which stars can be detected by the ESPRESSO spectrograph when used with an 8m VLT telescope, we need to calculate the signal-to-noise ratio (S/N) for each star. The condition is that the S/N must be at least 10 per binned pixel during a 1-hour exposure. First, let's recall the formula for the S/N in astro...
[{"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, we track the possible posit(...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 }
"To solve this problem, we need to determine the number of subarrays in a given array such that remo(...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 }
"To solve this problem, we need to determine the earliest moment when all lights in the apartment ar(...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 after each query, we toggle a vertex's color and (...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 }
"To solve this problem, we need to place Takahashi and the dragon parts in a grid such that all the (...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 }
"To solve this problem, we need to determine the probability that a randomly chosen point inside rec(...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_code_coder_stat_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 14.3 59.2 75.6 32.0 40.1 42.3 21.5 10.5 10.2

AIME24

  • Average Accuracy: 14.33% ± 1.25%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 10.00% 3 30
2 16.67% 5 30
3 20.00% 6 30
4 16.67% 5 30
5 16.67% 5 30
6 6.67% 2 30
7 16.67% 5 30
8 16.67% 5 30
9 10.00% 3 30
10 13.33% 4 30

AMC23

  • Average Accuracy: 59.25% ± 1.37%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 50.00% 20 40
2 62.50% 25 40
3 60.00% 24 40
4 67.50% 27 40
5 57.50% 23 40
6 57.50% 23 40
7 57.50% 23 40
8 62.50% 25 40
9 57.50% 23 40
10 60.00% 24 40

MATH500

  • Accuracy: 75.60%
    Accuracy Questions Solved Total Questions
    75.60% 378 500

MMLUPro

  • Average Accuracy: 32.00% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 32.00% 160 500

JEEBench

  • Average Accuracy: 40.15% ± 0.73%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 41.89% 215.75 515
2 39.56% 203.75 515
3 38.98% 200.75 515

GPQADiamond

  • Average Accuracy: 42.26% ± 1.13%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 40.40% 80 198
2 44.95% 89 198
3 41.41% 82 198

LiveCodeBench

  • Average Accuracy: 21.46% ± 1.20%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 21.14% 108 511
2 23.68% 121 511
3 19.57% 100 511

CodeElo

  • Average Accuracy: 10.49% ± 1.29%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 12.02% 47 391
2 11.51% 45 391
3 7.93% 31 391

CodeForces

  • Average Accuracy: 10.23% ± 1.18%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 12.58% 57 453
2 8.83% 40 453
3 9.27% 42 453
Downloads last month
10