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
193k
[ { "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 }
To identify the compound C9H11NO2 using the given data, let's analyze the IR and NMR spectra step by step. First, let's consider the IR spectrum: - Medium to strong bands at 3420 cm⁻¹ and 3325 cm⁻¹ are likely due to N-H stretching in amide groups. The fact that there are two bands suggests there might be two different...
[ { "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 have this equation to solve: \[\log_{7x}2023 \cdot \log_{289x}2023 = \log_{2023x}2023\] Hmm, logarithms with different bases. I remember that \(\log_b a = \frac{\ln a}{\ln b}\), so maybe I can convert all the logarithms to the natural logarithm to simplify the equation. Let me try that. First, le...
[ { "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 it again carefully. We have a 2D integer array called nums. Initially, our score is 0. We perform operations until the matrix is empty. Each operation involves two steps: 1. From each row, select the largest number and remove it. 2. Then, ...
[ { "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 figure out this problem step by step. So, we have three complexes: X, Y, and Z. Let me start by understanding each part of the problem. First, the problem says that when we add excess aqueous ammonia to a pink-colored aqueous solution of MCl₂·6H₂O (which is X) and NH₄Cl, we get an octahedral...
[{"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 whose asymptotes are (...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 \n\n\\[\n\\sqrt{\\fra(...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 }
"To solve this problem, we need to find all indices in the string `s` where a substring equal to `a`(...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 }
"```python\ndef print_b_values():\n import sys\n input = sys.stdin.read\n data = input().sp(...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 }
"from bisect import bisect_left\n\ndef solve():\n N, M = map(int, input().split())\n A = list((...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 me think abou(...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_metamath_eval_1331

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 GPQADiamond MMLUPro LiveCodeBench CodeElo JEEBench
Accuracy 13.7 58.0 74.2 39.6 28.8 9.8 2.5 34.4

AIME24

  • Average Accuracy: 13.67% ± 1.29%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 13.33% 4 30
2 16.67% 5 30
3 13.33% 4 30
4 13.33% 4 30
5 13.33% 4 30
6 3.33% 1 30
7 13.33% 4 30
8 13.33% 4 30
9 16.67% 5 30
10 20.00% 6 30

AMC23

  • Average Accuracy: 58.00% ± 2.17%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 57.50% 23 40
2 67.50% 27 40
3 57.50% 23 40
4 62.50% 25 40
5 50.00% 20 40
6 55.00% 22 40
7 70.00% 28 40
8 52.50% 21 40
9 60.00% 24 40
10 47.50% 19 40

MATH500

  • Accuracy: 74.20%
    Accuracy Questions Solved Total Questions
    74.20% 371 500

GPQADiamond

  • Average Accuracy: 39.56% ± 1.67%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 42.93% 85 198
2 39.90% 79 198
3 35.86% 71 198

MMLUPro

  • Average Accuracy: 28.80% ± 0.00%
  • Number of Runs: 1
Run Accuracy Questions Solved Total Questions
1 28.80% 144 500

LiveCodeBench

  • Average Accuracy: 9.78% ± 1.18%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 8.81% 45 511
2 8.41% 43 511
3 12.13% 62 511

CodeElo

  • Average Accuracy: 2.47% ± 0.37%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 1.79% 7 391
2 3.07% 12 391
3 2.56% 10 391

JEEBench

  • Average Accuracy: 34.42% ± 0.46%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 34.51% 177.75 515
2 35.34% 182.0 515
3 33.40% 172.0 515
Downloads last month
490