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
8
354k
[ { "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, I need to solve this problem where I have to find the strongest programmer based on the given relations. Hmm, let's think. So the problem says that the relations are transitive. That means the relationships form a partial order, right? But because of transitivity, it's like a total order? Wait, no. Becaus...
[ { "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, let's try to solve this problem step by step. So, we need to find the standard molar enthalpy of formation of HgO(s) at 298 K. The answer should be a numeric value correct up to the second decimal digit. Hmm, let's see. The problem gives us information about the combustion of Hg(g) in a bomb calorimeter, ...
[{"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's see. The problem is to maximize the number of points Kevin can earn by rearran(...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, let's try 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, I need to solve this problem where after each operation, I have to determine the num(...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, I need to solve this problem where I have to find the total number of incremovable s(...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, let's tackle this problem step by step. So, the task is to determine the earliest ti(...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 we have a tree of vertices with colors that can b(...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, I need to generate a Python function that takes stdin as input and prints the arrang(...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 solve this problem: Given a rectangle ABCD with center O, and the ratio(...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/316_globalbatchsize32_lr1e5_epochs11_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 18.3 55.8 73.6 28.0 41.5 42.8 23.8 4.9 6.5

AIME24

  • Average Accuracy: 18.33% ± 1.18%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 20.00% 6 30
2 23.33% 7 30
3 23.33% 7 30
4 16.67% 5 30
5 20.00% 6 30
6 16.67% 5 30
7 10.00% 3 30
8 16.67% 5 30
9 20.00% 6 30
10 16.67% 5 30

AMC23

  • Average Accuracy: 55.75% ± 1.84%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 65.00% 26 40
2 55.00% 22 40
3 50.00% 20 40
4 55.00% 22 40
5 57.50% 23 40
6 47.50% 19 40
7 60.00% 24 40
8 50.00% 20 40
9 65.00% 26 40
10 52.50% 21 40

MATH500

  • Accuracy: 73.60%
    Accuracy Questions Solved Total Questions
    73.60% 368 500

MMLUPro

  • Average Accuracy: 28.00% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 28.00% 140 500

JEEBench

  • Average Accuracy: 41.46% ± 0.48%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 40.29% 207.5 515
2 42.14% 217.0 515
3 41.94% 216.0 515

GPQADiamond

  • Average Accuracy: 42.76% ± 0.50%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 41.92% 83 198
2 42.42% 84 198
3 43.94% 87 198

LiveCodeBench

  • Average Accuracy: 23.81% ± 0.26%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 23.29% 119 511
2 24.07% 123 511
3 24.07% 123 511

CodeElo

  • Average Accuracy: 4.86% ± 0.77%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 4.09% 16 391
2 6.39% 25 391
3 4.09% 16 391

CodeForces

  • Average Accuracy: 6.48% ± 0.78%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 7.95% 36 453
2 6.18% 28 453
3 5.30% 24 453
Downloads last month
7