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
2.1k
234k
[ { "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 among N people based on given M superiority relationships. Hmm. Let's see the problem again. The key points are: - The superiority is a transitive relation, so it's like a partial order but with transitivity. Wait, no, actua...
[ { "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> Alright, so I have this problem here about the combustion of mercury gas to form mercury(II) oxide solid. Let me try to parse it step by step. First, the problem states that 2 moles of Hg(g) are combusted in a fixed volume bomb calorimeter with excess O₂ at 298 K, and the temperature rises from 298.0 K to 312...
[{"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> Okay, so I need to solve this programming problem where Kevin is trying to maximize his poi(...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> Okay, so I need to figure out how many of these stars can be detected by the ESPHmm... Wait(...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 Joker problem. Let's see what the problem is asking again. So, w(...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 figure out how to count all the subarrays of a given array that are \"in(...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 we have rooms with lights that are toggled by c(...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 of vertices, and I have to handle qu(...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 Python function that outputs the correct arrangement of the d(...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_ckpt03000_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 58.7 86.2 89.8 0.3 60.8 43.3 44.7 18.6 21.1

AIME24

  • Average Accuracy: 58.67% ± 2.37%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 50.00% 15 30
2 53.33% 16 30
3 60.00% 18 30
4 46.67% 14 30
5 66.67% 20 30
6 50.00% 15 30
7 63.33% 19 30
8 63.33% 19 30
9 66.67% 20 30
10 66.67% 20 30

AMC23

  • Average Accuracy: 86.25% ± 0.88%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 92.50% 37 40
2 85.00% 34 40
3 82.50% 33 40
4 85.00% 34 40
5 85.00% 34 40
6 85.00% 34 40
7 85.00% 34 40
8 87.50% 35 40
9 90.00% 36 40
10 85.00% 34 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: 60.76% ± 0.26%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 60.15% 309.75 515
2 61.21% 315.25 515
3 60.92% 313.75 515

GPQADiamond

  • Average Accuracy: 43.27% ± 0.77%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 41.41% 82 198
2 43.94% 87 198
3 44.44% 88 198

LiveCodeBench

  • Average Accuracy: 44.75% ± 1.07%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 46.58% 238 511
2 42.86% 219 511
3 44.81% 229 511

CodeElo

  • Average Accuracy: 18.58% ± 0.45%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 17.90% 70 391
2 19.44% 76 391
3 18.41% 72 391

CodeForces

  • Average Accuracy: 21.12% ± 0.19%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 21.41% 97 453
2 21.19% 96 453
3 20.75% 94 453
Downloads last month
3