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
1.78k
193k
[ { "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 determine the strongest programmer based on the given information. Hmm, let's see. The problem says that for any two distinct programmers, exactly one is stronger, and the relation is transitive. So the hierarchy forms a total order. But the given information m...
[ { "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 a combustion reaction in a bomb calorimeter. Let me try to parse this step by step. First, the reaction is 2 moles of Hg(g) being combusted with excess O₂ at 298 K and 1 atm into HgO...
[ { "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 }
<think> Okay, let's see. I need to solve this problem where Kevin is trying to maximize his points by rearranging the array of numbers. The points are earned when after adding a_i to s, which is initially 0, the resulting s is even. Then he divides by 2 until it's odd. But each operation can give at most one point. So ...
[{"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> Okay, so I need to figure out how many of these stars can be detected by the ESPRESSO spect(...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> Okay, I need to solve this problem where after each operation, I have to find the number of(...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> Okay, so I need to find the number of subarrays in a given array of positive integers such (...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> Okay, so I need to solve this problem where I have to find the earliest time when all the l(...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> Okay, I need to solve this problem where I have a tree and perform a series of toggle opera(...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> Okay, so I need to generate a grid where Takahashi is at the center, and all the dragon par(...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> Okay, so I have this problem about a rectangle ABCD with center O, and the ratio of AB to A(...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/openthoughts3_herorun_ckpt04500_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 63.0 91.3 89.8 0.3 64.9 47.3 53.8 24.0 25.3

AIME24

  • Average Accuracy: 63.00% ± 1.20%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 56.67% 17 30
2 60.00% 18 30
3 63.33% 19 30
4 63.33% 19 30
5 60.00% 18 30
6 60.00% 18 30
7 66.67% 20 30
8 70.00% 21 30
9 63.33% 19 30
10 66.67% 20 30

AMC23

  • Average Accuracy: 91.25% ± 0.88%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 85.00% 34 40
2 90.00% 36 40
3 92.50% 37 40
4 95.00% 38 40
5 92.50% 37 40
6 87.50% 35 40
7 92.50% 37 40
8 92.50% 37 40
9 92.50% 37 40
10 92.50% 37 40

MATH500

  • Accuracy: 89.80%
    Accuracy Questions Solved Total Questions
    89.80% 449 500

MMLUPro

  • Accuracy: 0.34%
    Accuracy Questions Solved Total Questions
    0.34% N/A N/A

JEEBench

  • Average Accuracy: 64.92% ± 1.06%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 62.62% 322.5 515
2 65.00% 334.75 515
3 67.14% 345.75 515

GPQADiamond

  • Average Accuracy: 47.31% ± 0.84%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 45.45% 90 198
2 48.99% 97 198
3 47.47% 94 198

LiveCodeBench

  • Average Accuracy: 53.75% ± 1.44%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 55.38% 283 511
2 50.88% 260 511
3 54.99% 281 511

CodeElo

  • Average Accuracy: 23.96% ± 0.60%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 25.06% 98 391
2 23.02% 90 391
3 23.79% 93 391

CodeForces

  • Average Accuracy: 25.31% ± 0.07%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 25.39% 115 453
2 25.17% 114 453
3 25.39% 115 453
Downloads last month
7