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
113
181k
[ { "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 solve this problem. Let me start by understanding the requirements. We have N competitive programmers, and we need to determine if there's a unique strongest programmer based on M given relations where one person is stronger than another. The relations are transitive, meanin...
[ { "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 relate the data provided to calculate ΔHf° for HgO. Let me start by recalling what I know about enthalpy changes and calor...
[{"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 }
"<think>\nOkay, let me try to figure out this problem. So, the task is about rearranging the given i(...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 would be detectable using the ESPRES(...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 n cards with a joker at posi(...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 solve this problem where there are n rooms each with a light initially (...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 bla(...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 generates a valid arrangement of dragon pa(...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_length_gpt4omini_1k_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 16.3 53.7 72.2 28.4 34.2 30.5 15.5 3.2 4.1

AIME24

  • Average Accuracy: 16.33% ± 1.60%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 13.33% 4 30
2 3.33% 1 30
3 13.33% 4 30
4 20.00% 6 30
5 20.00% 6 30
6 20.00% 6 30
7 16.67% 5 30
8 20.00% 6 30
9 16.67% 5 30
10 20.00% 6 30

AMC23

  • Average Accuracy: 53.75% ± 1.55%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 50.00% 20 40
2 45.00% 18 40
3 57.50% 23 40
4 57.50% 23 40
5 52.50% 21 40
6 50.00% 20 40
7 57.50% 23 40
8 62.50% 25 40
9 55.00% 22 40
10 50.00% 20 40

MATH500

  • Accuracy: 72.20%
    Accuracy Questions Solved Total Questions
    72.20% 361 500

MMLUPro

  • Average Accuracy: 28.40% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 28.40% 142 500

JEEBench

  • Average Accuracy: 34.21% ± 0.32%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 34.95% 180.0 515
2 33.59% 173.0 515
3 34.08% 175.5 515

GPQADiamond

  • Average Accuracy: 30.47% ± 1.82%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 31.31% 62 198
2 33.84% 67 198
3 26.26% 52 198

LiveCodeBench

  • Average Accuracy: 15.46% ± 0.52%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 15.66% 80 511
2 14.48% 74 511
3 16.24% 83 511

CodeElo

  • Average Accuracy: 3.24% ± 0.60%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 3.84% 15 391
2 2.05% 8 391
3 3.84% 15 391

CodeForces

  • Average Accuracy: 4.12% ± 0.48%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 3.75% 17 453
2 3.53% 16 453
3 5.08% 23 453
Downloads last month
6