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
12 values
metadata
dict
model_outputs
stringlengths
107
348k
[ { "content": "Problem: There are $n$ values of $x$ in the interval $0<x<2\\pi$ where $f(x)=\\sin(7\\pi\\cdot\\sin(5x))=0$. For $t$ of these $n$ values of $x$, the graph of $y=f(x)$ is tangent to the $x$-axis. Find $n+t$.\nMark your solution with \\boxed\nAnswer:", "role": "user" } ]
{ "do_sample": false, "max_new_tokens": 32768, "seed": 9, "temperature": 0.7 }
9
23
AIME25
{ "expected_answer": "149", "problem_id": "II-9", "reference_rationale": null, "reference_solution": "", "subject": null, "type": null }
<think> Okay, so I need to solve this problem where there's a function f(x) = sin(7π·sin(5x)), and we need to find the number of points in the interval 0 < x < 2π where f(x) = 0. Then, among those points, some are points where the graph is tangent to the x-axis. We need to find how many such tangent points there are an...
[ { "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 th...
{ "do_sample": false, "max_new_tokens": 32768, "seed": 2, "temperature": 0.7 }
2
88
CodeElo
{ "expected_answer": "", "problem_id": "", "reference_rationale": null, "reference_solution": "", "subject": null, "type": null }
<think> Okay, so I need to solve this problem where I have to count the number of nonempty strings t (not equal to "a") such that the input string s can be partitioned into some substrings, each of which is either t or "a", with at least one t. Let me try to understand the problem step by step. First, the problem says...
[ { "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 th...
{ "do_sample": false, "max_new_tokens": 32768, "seed": 1, "temperature": 0.7 }
1
40
CodeElo
{ "expected_answer": "", "problem_id": "", "reference_rationale": null, "reference_solution": "", "subject": null, "type": null }
<think> Okay, let me try to figure out this problem. So, we have a permutation of size n, and we perform q operations where each operation splits a single array into two parts, keeping track of the maximum elements in the left and right parts (l_i and r_i). We need to determine how many permutations are valid given the...
[{"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
104
CodeForces
{"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED)
"<think>\nOkay, let me try to figure out this problem. So, we have a 2xN matrix, and we can swap col(...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
378
CodeElo
{"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED)
"<think>\nOkay, so I need to figure out how to construct a permutation of numbers from 1 to n that m(...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
49
CodeElo
{"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED)
"<think>\nOkay, so I need to figure out for each candidate i, the minimum number of candidates to ex(...TRUNCATED)
[{"content":"Your response should be in the following format:\nExplanation: {your explanation for yo(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 2, "temperature": 0.7 }
2
120
HLESubset
{"expected_answer":"B","problem_id":"670013827794cc36bc974f27","reference_rationale":"B cell product(...TRUNCATED)
"<think>\nOkay, let's try to figure out this problem step by step. So, the question is about the dyn(...TRUNCATED)
[{"content":"Your response should be in the following format:\nExplanation: {your explanation for yo(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 0, "temperature": 0.7 }
0
223
HLESubset
{"expected_answer":"G","problem_id":"671d9e9d29e7fde7166e474d","reference_rationale":"1. Metals.\nIt(...TRUNCATED)
"<think>\nOkay, let's try to figure out the function of molecule Al1, Al2, and Rga1 based on the pro(...TRUNCATED)
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 0, "temperature": 0.7 }
0
111
LiveCodeBenchV5
{"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED)
"<think>\nOkay, so I need to figure out how to solve this problem where I have to calculate the sum (...TRUNCATED)
[{"content":"In this problem, multiple options can be correct. Give a detailed solution and end the (...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 2, "temperature": 0.7 }
2
35
JEEBench
{"expected_answer":"ABC","problem_id":"48","reference_rationale":null,"reference_solution":null,"sub(...TRUNCATED)
"<think>\nOkay, so I need to solve this geometry problem. Let me start by understanding what's given(...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/OpenR1-Qwen-7B_eval_2e29

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces AIME25 HLE LiveCodeBenchv5
Accuracy 52.7 85.2 86.8 26.0 64.4 46.5 9.8 2.8 1.6 33.7 1.9 6.2

AIME24

  • Average Accuracy: 52.67% ± 1.40%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 56.67% 17 30
2 43.33% 13 30
3 50.00% 15 30
4 53.33% 16 30
5 53.33% 16 30
6 56.67% 17 30
7 60.00% 18 30
8 50.00% 15 30
9 53.33% 16 30
10 50.00% 15 30

AMC23

  • Average Accuracy: 85.25% ± 0.83%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 85.00% 34 40
2 82.50% 33 40
3 87.50% 35 40
4 82.50% 33 40
5 85.00% 34 40
6 80.00% 32 40
7 87.50% 35 40
8 87.50% 35 40
9 87.50% 35 40
10 87.50% 35 40

MATH500

  • Accuracy: 86.80%
    Accuracy Questions Solved Total Questions
    86.80% 434 500

MMLUPro

  • Average Accuracy: 26.00% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 26.00% 130 500

JEEBench

  • Average Accuracy: 64.37% ± 0.56%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 64.22% 330.75 515
2 65.63% 338.0 515
3 63.25% 325.75 515

GPQADiamond

  • Average Accuracy: 46.46% ± 0.41%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 45.45% 90 198
2 46.97% 93 198
3 46.97% 93 198

LiveCodeBench

  • Average Accuracy: 9.78% ± 0.30%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 9.20% 47 511
2 9.98% 51 511
3 10.18% 52 511

CodeElo

  • Average Accuracy: 2.81% ± 0.15%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 2.56% 10 391
2 3.07% 12 391
3 2.81% 11 391

CodeForces

  • Average Accuracy: 1.62% ± 0.32%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 2.21% 10 453
2 1.55% 7 453
3 1.10% 5 453

AIME25

  • Average Accuracy: 33.67% ± 1.97%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 40.00% 12 30
2 36.67% 11 30
3 30.00% 9 30
4 36.67% 11 30
5 33.33% 10 30
6 33.33% 10 30
7 20.00% 6 30
8 26.67% 8 30
9 40.00% 12 30
10 40.00% 12 30

HLE

  • Average Accuracy: 1.89% ± 0.70%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 0.59% 3 512
2 1.56% 8 512
3 3.52% 18 512

LiveCodeBenchv5

  • Average Accuracy: 6.23% ± 0.95%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 5.15% 19 369
2 5.42% 20 369
3 8.13% 30 369
Downloads last month
6