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
8 values
metadata
dict
model_outputs
stringlengths
1
199k
[ { "content": "Return your final response within \\boxed{} and only include the letter choice (A, B, C, or D) as your final response.\nProblem: Identify the compound C9H11NO2 using the given data.\nIR: medium to strong intensity bands at 3420 cm-1, 3325 cm-1\nstrong band at 1720 cm-1\n1H NMR: 1.20 ppm (t, 3H); 4...
{ "do_sample": true, "max_new_tokens": 32768, "seed": 2, "temperature": 0.7 }
2
46
GPQADiamond
{ "expected_answer": "", "problem_id": "", "reference_solution": "", "subject": null, "type": null }
<think> Okay, so I need to figure out which compound among the options A to D is C9H11NO2 based on the given IR and NMR spectra. Let me start by recalling what each spectrum tells me. First, the IR spectrum. The medium to strong bands at 3420 and 3325 cm-1 are in the region where hydroxyl or amine groups absorb. Since...
[ { "content": "Problem: What is the product of all solutions to the equation\n\\[\\log_{7x}2023\\cdot \\log_{289x}2023=\\log_{2023x}2023\\]\nMark your solution with \\boxed\nAnswer:", "role": "user" } ]
{ "do_sample": false, "max_new_tokens": 32768, "seed": 3, "temperature": 0.7 }
3
8
AMC23
{ "expected_answer": "1", "problem_id": "10", "reference_solution": "", "subject": null, "type": null }
<think> Okay, so I need to solve this logarithmic equation: \[\log_{7x}2023 \cdot \log_{289x}2023 = \log_{2023x}2023\] Hmm, logarithms with different bases. Let me recall some logarithm properties. Maybe I can convert all these logarithms to the same base to make it easier? Or maybe use the change of base formula. L...
[ { "content": "Generate an executable Python function generated from the given prompt. Return the function body without invoking it at the final solution.You are given a 0-indexed 2D integer array nums. Initially, your score is 0. Perform the following operations until the matrix becomes empty:\n\nFrom each row ...
{ "do_sample": false, "max_new_tokens": 32768, "seed": 0, "temperature": 0.7 }
0
10
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "", "subject": null, "type": null }
<think> Okay, so I need to figure out how to solve this problem. Let me read the description again carefully. We have a 2D integer array (matrix) and we want to compute a score by repeatedly removing the largest number from each row, then adding the largest of those removed numbers to our score, until the matrix is emp...
[ { "content": "In this problem, multiple options can be correct. Give a detailed solution and end the solution with the final answer. Mark your solution, which should be one or more multiple-choice letter(s), with \\boxed\nAnswer:\n\nProblem: Addition of excess aqueous ammonia to a pink coloured aqueous solution...
{ "do_sample": false, "max_new_tokens": 32768, "seed": 0, "temperature": 0.7 }
0
78
JEEBench
{ "expected_answer": "BCD", "problem_id": "23", "reference_solution": null, "subject": "chem", "type": "MCQ(multiple)" }
<think> Okay, let's try to tackle this problem step by step. First, I need to understand what each complex (X, Y, Z) is and how they relate to each other. Let me start by breaking down the information given. We have an aqueous solution of X, which is MCl₂·6H₂O, colored pink. Adding excess aqueous ammonia and NH₄Cl to ...
[{"content":"Problem: The asymptotes of a hyperbola are $y = 2x - 3$ and $y = 17 - 2x.$ Also, the h(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 0, "temperature": 0.7 }
0
409
MATH500
{ "expected_answer": "", "problem_id": "", "reference_solution": "", "subject": null, "type": null }
"<think>\nOkay, so I need to find the distance between the foci of a hyperbola given its asymptotes (...TRUNCATED)
[{"content":"Problem: For how many integers $n$ does the expression\\[\\sqrt{\\frac{\\log (n^2) - (\(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 0, "temperature": 0.7 }
0
37
AMC23
{ "expected_answer": "901", "problem_id": "47", "reference_solution": "", "subject": null, "type": null }
"<think>\nOkay, so I need to figure out for how many integers n the expression sqrt[(log(n²) - (log(...TRUNCATED)
[{"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
163
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "", "subject": null, "type": null }
"<think>\nOkay, so I need to solve this problem where I have a string s and two other strings a and (...TRUNCATED)
[{"content":"Generate an executable Python function generated from the given prompt. The function sh(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 2, "temperature": 0.7 }
2
410
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "", "subject": null, "type": null }
"def multiply_adjacent_pairs():\n import sys\n\n # Read input from standard input\n N = int(...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
313
LiveCodeBench
{ "expected_answer": "", "problem_id": "", "reference_solution": "", "subject": null, "type": null }
"<think>\nOkay, let's see. I need to figure out the maximum number of gifts I can collect by choosin(...TRUNCATED)
[{"content":"Problem: Simplify $\\tan 100^\\circ + 4 \\sin 100^\\circ.$\nMark your solution with \\b(...TRUNCATED)
{ "do_sample": false, "max_new_tokens": 32768, "seed": 0, "temperature": 0.7 }
0
164
MATH500
{ "expected_answer": "", "problem_id": "", "reference_solution": "", "subject": null, "type": null }
"<think>\nOkay, so I need to simplify the expression tan 100° + 4 sin 100°. Hmm, let's see. I reme(...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/a1_math_hendrycks_eval_1331

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo
Accuracy 19.7 59.0 79.4 31.2 37.6 38.2 15.1 3.8

AIME24

  • Average Accuracy: 19.67% ± 1.20%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 16.67% 5 30
2 20.00% 6 30
3 26.67% 8 30
4 13.33% 4 30
5 23.33% 7 30
6 20.00% 6 30
7 16.67% 5 30
8 23.33% 7 30
9 20.00% 6 30
10 16.67% 5 30

AMC23

  • Average Accuracy: 59.00% ± 1.38%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 57.50% 23 40
2 65.00% 26 40
3 65.00% 26 40
4 57.50% 23 40
5 60.00% 24 40
6 62.50% 25 40
7 60.00% 24 40
8 57.50% 23 40
9 50.00% 20 40
10 55.00% 22 40

MATH500

  • Accuracy: 79.40%
    Accuracy Questions Solved Total Questions
    79.40% 397 500

MMLUPro

  • Average Accuracy: 31.20% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 31.20% 156 500

JEEBench

  • Average Accuracy: 37.59% ± 0.42%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 37.57% 193.5 515
2 38.50% 198.25 515
3 36.70% 189.0 515

GPQADiamond

  • Average Accuracy: 38.22% ± 0.73%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 37.88% 75 198
2 36.87% 73 198
3 39.90% 79 198

LiveCodeBench

  • Average Accuracy: 15.07% ± 1.26%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 17.42% 89 511
2 14.68% 75 511
3 13.11% 67 511

CodeElo

  • Average Accuracy: 3.84% ± 0.30%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 3.84% 15 391
2 3.32% 13 391
3 4.35% 17 391
Downloads last month
3