Dataset Viewer
Auto-converted to Parquet Duplicate
context
list
gen_kwargs
dict
repeat_idx
int64
request_idx
int64
task_name
string
metadata
dict
model_outputs
string
[ { "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 write a Python function that reads from stdin and determines the strongest programmer. Let's think about how to model this problem. The key points are that the relations are transitive and form a strict total order. Wait, but the problem says that there's exactly one strongest person. So even t...
[ { "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. First, I need to understand what's being asked. We have to find the standard molar enthalpy of formation of HgO(s) at 298 K, given some reaction data and other values. The final answer should be a numerical value correct up to two decimal digits, enclosed in a...
[{"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 rearrange the array a so that the number of points Kevi(...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 find the number o(...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 number of incremovable subarra(...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. So, the task is to find the earliest time when all lights(...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 I have to handle queries on a tree and determine (...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 write a Python function that reads N from stdin and generates a grid accor(...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/1k_globalbatchsize96_lr1e5_epochs11_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 15.3 60.8 76.4 28.8 44.4 41.4 24.5 5.7 6.4

AIME24

  • Average Accuracy: 15.33% ± 1.17%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 10.00% 3 30
2 13.33% 4 30
3 16.67% 5 30
4 13.33% 4 30
5 10.00% 3 30
6 20.00% 6 30
7 16.67% 5 30
8 13.33% 4 30
9 20.00% 6 30
10 20.00% 6 30

AMC23

  • Average Accuracy: 60.75% ± 1.87%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 62.50% 25 40
2 72.50% 29 40
3 65.00% 26 40
4 65.00% 26 40
5 62.50% 25 40
6 50.00% 20 40
7 57.50% 23 40
8 57.50% 23 40
9 60.00% 24 40
10 55.00% 22 40

MATH500

  • Accuracy: 76.40%
    Accuracy Questions Solved Total Questions
    76.40% 382 500

MMLUPro

  • Average Accuracy: 28.80% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 28.80% 144 500

JEEBench

  • Average Accuracy: 44.37% ± 0.82%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 42.48% 218.75 515
2 45.92% 236.5 515
3 44.71% 230.25 515

GPQADiamond

  • Average Accuracy: 41.41% ± 0.86%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 41.92% 83 198
2 42.93% 85 198
3 39.39% 78 198

LiveCodeBench

  • Average Accuracy: 24.46% ± 0.41%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 25.24% 129 511
2 24.27% 124 511
3 23.87% 122 511

CodeElo

  • Average Accuracy: 5.71% ± 0.37%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 5.12% 20 391
2 6.39% 25 391
3 5.63% 22 391

CodeForces

  • Average Accuracy: 6.40% ± 0.56%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 5.96% 27 453
2 7.51% 34 453
3 5.74% 26 453
Downloads last month
3