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
152k
[ { "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 }
def strongest_programmer(): import sys input = sys.stdin.read N, M = map(int, input().split()) relations = [list(map(int, input().split())) for _ in range(M)] # Create a graph to represent the relations graph = {i: set() for i in range(1, N+1)} for A, B in relations: graph[A].ad...
[ { "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 in a bomb calorimeter. Let me try to break this down step by step. First, the reaction is 2 mol of Hg(g) combusted in a fixed volume bomb calorimeter with exce...
[ { "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 }
To solve this problem, we need to determine the maximum number of points Kevin can earn by rearranging the integers in such a way that maximizes the number of times he adds an even number (which allows him to earn a point by repeatedly dividing by 2 until the sum becomes odd). Here's the step-by-step approach: 1. **Un...
[{"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 are detectable using the ESPRESSO sp(...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 we have a deck of cards with a joker at positi(...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 }
"def incremovableSubarrayCount(nums):\n def isStrictlyIncreasing(arr):\n return all(arr[i](...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 }
"Okay, let's tackle this problem step by step. The problem is about determining the earliest moment (...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 \"Chain Queries\" problem. Let me start by understanding the(...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 }
"def solve():\n import sys\n input = sys.stdin.read\n N = int(input().strip())\n\n def m(...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 determine the probability that a randomly chosen point from the interior of 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_science_camel_chemistry_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 16.3 49.8 73.2 26.8 37.5 34.7 1.4 3.8 5.6

AIME24

  • Average Accuracy: 16.33% ± 1.10%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 10.00% 3 30
2 13.33% 4 30
3 20.00% 6 30
4 20.00% 6 30
5 20.00% 6 30
6 16.67% 5 30
7 20.00% 6 30
8 13.33% 4 30
9 16.67% 5 30
10 13.33% 4 30

AMC23

  • Average Accuracy: 49.75% ± 1.82%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 50.00% 20 40
2 45.00% 18 40
3 45.00% 18 40
4 60.00% 24 40
5 45.00% 18 40
6 55.00% 22 40
7 50.00% 20 40
8 52.50% 21 40
9 40.00% 16 40
10 55.00% 22 40

MATH500

  • Accuracy: 73.20%
    Accuracy Questions Solved Total Questions
    73.20% 366 500

MMLUPro

  • Average Accuracy: 26.80% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 26.80% 134 500

JEEBench

  • Average Accuracy: 37.46% ± 1.31%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 38.74% 199.5 515
2 34.27% 176.5 515
3 39.37% 202.75 515

GPQADiamond

  • Average Accuracy: 34.68% ± 0.50%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 33.84% 67 198
2 34.34% 68 198
3 35.86% 71 198

LiveCodeBench

  • Average Accuracy: 1.44% ± 0.91%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 3.13% 16 511
2 1.17% 6 511
3 0.00% 0 511

CodeElo

  • Average Accuracy: 3.75% ± 0.09%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 3.84% 15 391
2 3.84% 15 391
3 3.58% 14 391

CodeForces

  • Average Accuracy: 5.59% ± 0.39%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 4.86% 22 453
2 6.18% 28 453
3 5.74% 26 453
Downloads last month
19