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
73
184k
[ { "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 how to determine the strongest programmer among N people based on M pieces of information about their superiority. The problem says that the relations are transitive, and there's exactly one strongest person. If the information given leads to a unique strongest person, I should pri...
[ { "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 the combustion of Hg(g) in a bomb calorimeter, and I have to use that data along with the heat capacity of the calorimeter and the enthalpy of formation of Hg(g) to calculate it. Let ...
[{"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 }
"Okay, so I need to figure out how to maximize the number of points Kevin can earn by rearranging th(...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 can be detected by the ESPRESSO spec(...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 to solve this problem where I have to find the total num(...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 how to solve this problem where there are multiple rooms eac(...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 problem where I have a tree with vertices colored either whi(...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 write a Python function that arranges dragon parts and Takahashi on an (...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_science_fasttext_pos_scp116k_1k_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 16.3 51.0 71.6 26.4 36.5 32.2 18.7 2.6 4.2

AIME24

  • Average Accuracy: 16.33% ± 1.29%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 13.33% 4 30
2 13.33% 4 30
3 20.00% 6 30
4 10.00% 3 30
5 16.67% 5 30
6 13.33% 4 30
7 23.33% 7 30
8 20.00% 6 30
9 13.33% 4 30
10 20.00% 6 30

AMC23

  • Average Accuracy: 51.00% ± 1.38%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 50.00% 20 40
2 50.00% 20 40
3 47.50% 19 40
4 50.00% 20 40
5 57.50% 23 40
6 45.00% 18 40
7 60.00% 24 40
8 52.50% 21 40
9 50.00% 20 40
10 47.50% 19 40

MATH500

  • Accuracy: 71.60%
    Accuracy Questions Solved Total Questions
    71.60% 358 500

MMLUPro

  • Average Accuracy: 26.40% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 26.40% 132 500

JEEBench

  • Average Accuracy: 36.54% ± 0.68%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 36.55% 188.25 515
2 37.96% 195.5 515
3 35.10% 180.75 515

GPQADiamond

  • Average Accuracy: 32.15% ± 0.69%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 31.31% 62 198
2 31.31% 62 198
3 33.84% 67 198

LiveCodeBench

  • Average Accuracy: 18.66% ± 1.26%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 21.14% 108 511
2 17.03% 87 511
3 17.81% 91 511

CodeElo

  • Average Accuracy: 2.64% ± 0.09%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 2.56% 10 391
2 2.81% 11 391
3 2.56% 10 391

CodeForces

  • Average Accuracy: 4.19% ± 0.25%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 4.64% 21 453
2 3.75% 17 453
3 4.19% 19 453
Downloads last month
4