Dataset Viewer
Auto-converted to Parquet Duplicate
context
listlengths
1
1
gen_kwargs
dict
repeat_idx
int64
0
9
request_idx
int64
0
12k
task_name
stringclasses
12 values
metadata
dict
model_outputs
stringlengths
432
696k
[ { "content": "The following are multiple choice questions (with answers) about math. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n\n\n\nQuestion:\nThe symmetric group $S_n$ has $\n\\factorial{n}$ elements, hence it is not true that $S_{10}$ has...
{ "do_sample": null, "max_new_tokens": 2048, "seed": 0, "temperature": 0 }
0
8,357
MMLUPro
{ "expected_answer": "", "problem_id": "", "reference_rationale": null, "reference_solution": "", "subject": null, "type": null }
<think> Okay, let's tackle this question about the confidence interval. The question is asking which interpretation of the 95% confidence interval ($35,095, $45,005) is correct. The options provided are A through J. I need to recall what a confidence interval actually means, especially in the context of estimating the ...
[ { "content": "The following are multiple choice questions (with answers) about business. Think step by step and then finish your answer with \"the answer is (X)\" where X is the correct letter choice.\n\n\n\nQuestion:\nIn contrast to _______, _______ aim to reward favourable behaviour by companies. The success ...
{ "do_sample": null, "max_new_tokens": 2048, "seed": 0, "temperature": 0 }
0
499
MMLUPro
{ "expected_answer": "", "problem_id": "", "reference_rationale": null, "reference_solution": "", "subject": null, "type": null }
<think> Okay, let's tackle this question about intrinsic value of a preferred stock. Hmm, so the question is asking for the intrinsic value given a dividend of $1.90 per year and a required rate of return of 9%. Alright, I remember from finance class that the intrinsic value of a preferred stock can be calculated using...
[ { "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
155
CodeElo
{ "expected_answer": "", "problem_id": "", "reference_rationale": null, "reference_solution": "", "subject": null, "type": null }
<think> Okay, let's see. I need to solve this problem where a robot moves in a grid and changes direction when it hits a wall. The task is to count how many times it returns to (0,0) when the script is executed k times. Hmm. First, let me understand the problem again. The robot starts at (0,0), and for each of the k ...
[ { "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.For a positive integer N, let V_N be the integer formed by concatenating N exactly N times.\r\nMore precisely, conside...
{ "do_sample": false, "max_new_tokens": 32768, "seed": 2, "temperature": 0.7 }
2
7
LiveCodeBenchV5
{ "expected_answer": "", "problem_id": "", "reference_rationale": null, "reference_solution": "", "subject": null, "type": null }
<think> Okay, so I need to solve this problem where given a positive integer N, I have to compute V_N mod 998244353. V_N is formed by concatenating N exactly N times. For example, if N is 3, then V_3 is 333, and if N is 10, it's 10101010101010101010. The modulus is a large prime, so I need to compute this efficiently e...
[{"content":"Generate an executable Python function generated from the given prompt. Return the func(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 1, "temperature": 0.7 }
1
167
LiveCodeBench
{"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED)
"<think> Okay, let's see. I need to find the number of subarrays that are \"incremovable\". The defi(...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": 1, "temperature": 0.7 }
1
143
CodeForces
{"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED)
"<think> Okay, let's see. I need to solve this problem where we have to determine after each update (...TRUNCATED)
[{"content":"Problem: Carlos went to a sports store to buy running shoes. Running shoes were on sale(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 0, "temperature": 0.7 }
0
30
AMC23
{"expected_answer":"50","problem_id":"36","reference_rationale":null,"reference_solution":"","subjec(...TRUNCATED)
"<think> Okay, so Carlos wants to buy some running shoes, and they're on sale with 20% off. But ther(...TRUNCATED)
[{"content":"The following are multiple choice questions (with answers) about law. Think step by ste(...TRUNCATED)
{ "do_sample": null, "max_new_tokens": 2048, "seed": 0, "temperature": 0 }
0
1,256
MMLUPro
{"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED)
"<think> Okay, let's tackle this question about the deed and figure out who is entitled to the proce(...TRUNCATED)
[{"content":"The following are multiple choice questions (with answers) about law. Think step by ste(...TRUNCATED)
{ "do_sample": null, "max_new_tokens": 2048, "seed": 0, "temperature": 0 }
0
1,219
MMLUPro
{"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED)
"<think> Okay, let's tackle this question step by step. The scenario involves a family property disp(...TRUNCATED)
[{"content":"The following are multiple choice questions (with answers) about philosophy. Think step(...TRUNCATED)
{ "do_sample": null, "max_new_tokens": 2048, "seed": 0, "temperature": 0 }
0
10,779
MMLUPro
{"expected_answer":"","problem_id":"","reference_rationale":null,"reference_solution":"","subject":n(...TRUNCATED)
"<think> Okay, let's tackle this question. The question is about Little's argument regarding the pre(...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_30k_leonardo_sharegpt_eval_2e29

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces AIME25 HLE LiveCodeBenchv5
Accuracy 47.0 78.2 85.8 12.4 58.7 44.3 43.8 17.0 19.3 33.3 8.1 31.3

AIME24

  • Average Accuracy: 47.00% ± 1.52%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 43.33% 13 30
2 53.33% 16 30
3 43.33% 13 30
4 50.00% 15 30
5 43.33% 13 30
6 43.33% 13 30
7 43.33% 13 30
8 50.00% 15 30
9 43.33% 13 30
10 56.67% 17 30

AMC23

  • Average Accuracy: 78.25% ± 0.94%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 75.00% 30 40
2 80.00% 32 40
3 80.00% 32 40
4 80.00% 32 40
5 77.50% 31 40
6 72.50% 29 40
7 82.50% 33 40
8 75.00% 30 40
9 80.00% 32 40
10 80.00% 32 40

MATH500

  • Accuracy: 85.80%
    Accuracy Questions Solved Total Questions
    85.80% 429 500

MMLUPro

  • Average Accuracy: 12.40% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 12.40% 62 500

JEEBench

  • Average Accuracy: 58.71% ± 0.73%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 58.64% 302.0 515
2 60.29% 310.5 515
3 57.18% 294.5 515

GPQADiamond

  • Average Accuracy: 44.28% ± 0.77%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 42.42% 84 198
2 44.95% 89 198
3 45.45% 90 198

LiveCodeBench

  • Average Accuracy: 43.77% ± 1.50%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 46.77% 239 511
2 42.47% 217 511
3 42.07% 215 511

CodeElo

  • Average Accuracy: 16.97% ± 0.52%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 16.88% 66 391
2 16.11% 63 391
3 17.90% 70 391

CodeForces

  • Average Accuracy: 19.28% ± 0.97%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 19.65% 89 453
2 20.75% 94 453
3 17.44% 79 453

AIME25

  • Average Accuracy: 33.33% ± 2.00%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 33.33% 10 30
2 46.67% 14 30
3 40.00% 12 30
4 36.67% 11 30
5 23.33% 7 30
6 30.00% 9 30
7 33.33% 10 30
8 26.67% 8 30
9 30.00% 9 30
10 33.33% 10 30

HLE

  • Average Accuracy: 8.14% ± 0.47%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 7.03% 36 512
2 8.40% 43 512
3 8.98% 46 512

LiveCodeBenchv5

  • Average Accuracy: 31.35% ± 1.07%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 29.27% 108 369
2 32.79% 121 369
3 31.98% 118 369
Downloads last month
3