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
1.62k
641k
[ { "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 if there's a unique strongest programmer based on the given comparisons. Hmm. Let's see the problem again. The problem says that there are N programmers, and for every pair, exactly one is stronger. The superiority is transitive. So, the structure h...
[ { "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) using the information given. Let me start by writing down all the given data and then figure out the steps required to solve the problem. First, the problem states that 2 moles of Hg(g) are combusted in a fixed volume bomb calorimeter w...
[ { "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 the points by rearranging the array. The problem says that each time he adds an a_i to s, and if the result is even, he gets a point and then divides s by 2 repeatedly until it's odd. The goal is to arrange the array so that the tot...
[ { "content": "Return your final response within \\boxed{} and only include the letter choice (A, B, C, or D) as your final response.\nProblem: How many of the stars listed below would be detectable using the ESPRESSO spectrograph, when it is coupled with one of the 8m VLT telescopes at the Paranal Observatory? ...
{ "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 spectrograph with the VLT. The key here is the signal-to-noise ratio (S/N) needing to be at least 10 per binned pixel in a 1-hour exposure. Let me start by recalling what factors affect the S/N ratio for a star observed with 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": 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 solve this problem where I have to find the number of subarrays in the g(...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 to find the earliest time when all the (...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 after each query, I have to determine if the black(...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 placed at the center, and all other 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_ckpt01500_eval_636d

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces
Accuracy 46.7 83.0 86.6 0.4 53.9 41.9 42.1 15.2 16.6

AIME24

  • Average Accuracy: 46.67% ± 1.94%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 40.00% 12 30
2 46.67% 14 30
3 53.33% 16 30
4 40.00% 12 30
5 46.67% 14 30
6 56.67% 17 30
7 46.67% 14 30
8 53.33% 16 30
9 36.67% 11 30
10 46.67% 14 30

AMC23

  • Average Accuracy: 83.00% ± 1.57%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 75.00% 30 40
2 92.50% 37 40
3 80.00% 32 40
4 85.00% 34 40
5 90.00% 36 40
6 80.00% 32 40
7 80.00% 32 40
8 82.50% 33 40
9 80.00% 32 40
10 85.00% 34 40

MATH500

  • Accuracy: 86.60%
    Accuracy Questions Solved Total Questions
    86.60% 433 500

MMLUPro

  • Accuracy: 0.41%
    Accuracy Questions Solved Total Questions
    0.41% N/A N/A

JEEBench

  • Average Accuracy: 53.87% ± 0.63%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 53.30% 274.5 515
2 55.39% 285.25 515
3 52.91% 272.5 515

GPQADiamond

  • Average Accuracy: 41.92% ± 0.71%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 41.92% 83 198
2 40.40% 80 198
3 43.43% 86 198

LiveCodeBench

  • Average Accuracy: 42.14% ± 0.51%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 41.29% 211 511
2 43.05% 220 511
3 42.07% 215 511

CodeElo

  • Average Accuracy: 15.17% ± 0.37%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 14.58% 57 391
2 15.09% 59 391
3 15.86% 62 391

CodeForces

  • Average Accuracy: 16.63% ± 0.19%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 17.00% 77 453
2 16.34% 74 453
3 16.56% 75 453
Downloads last month
3