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
9
176k
[ { "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 }
<|python-ify|> from typing import List, Set, Dict, Union, Tuple import sys def find_strongest(n: int, m: int, relations: List[Tuple[int, int]]) -> int: superior: Dict[int, Set[int]] = {i: set() for i in range(1, n + 1)} inferior: Dict[int, Set[int]] = {i: set() for i in range(1, n + 1)} for a, b in relati...
[ { "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 data, like the heat capacity of the bomb calorimeter, the enthalpy of formation of Hg(g), the temperature change, and the gas constant. Let me try to piece this together step by step. First, the react...
[ { "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 array of integers. The key steps involve calculating the number of even and odd numbers in the array. Here's the breakdown: 1. **Input Reading**: First, we read the number of test cases and then process each test...
[ { "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 on the VLT telescopes at Paranal. The key criterion is a signal-to-noise ratio (S/N) of at least 10 per binned pixel over a 1-hour exposure. Let me start by recalling what I know about the ESPRESSO instrument ...
[ { "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": 0, "temperature": 0.7 }
0
321
CodeForces
{ "expected_answer": "", "problem_id": "", "reference_solution": "", "subject": null, "type": null }
To solve this problem, we need to track the possible positions of the joker after each operation on the deck. The key idea is to maintain the current possible segments where the joker can be located and update them as operations are performed. ### Approach 1. **Initial Segment**: Start with a single segment containin...
[{"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 count the number of incremovable subarrays in a given(...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 time when all lights in an apartment are t(...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 }
"To solve this problem, we need to determine after each query whether all black vertices form a chai(...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 }
"<language:python>\ndef func():\n import sys\n input = sys.stdin.read\n input()\n N = in(...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_science_fineweb_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 15.3 54.2 75.6 27.4 36.6 41.1 16.0 3.3 5.3

AIME24

  • Average Accuracy: 15.33% ± 1.51%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 10.00% 3 30
2 6.67% 2 30
3 16.67% 5 30
4 20.00% 6 30
5 23.33% 7 30
6 13.33% 4 30
7 16.67% 5 30
8 13.33% 4 30
9 20.00% 6 30
10 13.33% 4 30

AMC23

  • Average Accuracy: 54.25% ± 1.42%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 57.50% 23 40
2 47.50% 19 40
3 55.00% 22 40
4 55.00% 22 40
5 47.50% 19 40
6 57.50% 23 40
7 62.50% 25 40
8 55.00% 22 40
9 50.00% 20 40
10 55.00% 22 40

MATH500

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

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: 36.55% ± 0.74%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 34.76% 179.0 515
2 37.72% 194.25 515
3 37.18% 191.5 515

GPQADiamond

  • Average Accuracy: 41.08% ± 0.84%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 42.93% 85 198
2 40.91% 81 198
3 39.39% 78 198

LiveCodeBench

  • Average Accuracy: 16.05% ± 1.18%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 15.07% 77 511
2 14.68% 75 511
3 18.40% 94 511

CodeElo

  • Average Accuracy: 3.32% ± 0.68%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 2.30% 9 391
2 3.07% 12 391
3 4.60% 18 391

CodeForces

  • Average Accuracy: 5.30% ± 0.56%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 5.74% 26 453
2 4.19% 19 453
3 5.96% 27 453
Downloads last month
3