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
9
178k
[ { "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 of the options A to D is the compound C9H11NO2. Let me start by looking at the IR and NMR data provided. First, the IR spectrum has medium to strong bands at 3420 and 3325 cm^-1, and a strong band at 1720 cm^-1. The 1720 cm^-1 is probably the carbonyl group, which is common ...
[ { "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 equation: \[ \log_{7x}2023 \cdot \log_{289x}2023 = \log_{2023x}2023 \] Hmm, logarithms with different bases. Maybe I can use some change of base formula to make the bases the same? Let me recall the change of base formula. It says that \(\log_a b = \frac{\ln b}{\ln a}\), right? ...
[ { "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, I need to create a Python function that calculates the final score based on the given matrix operations. Let me break down the problem step by step. First, the input is a 2D integer array called nums. The score starts at 0. The operations to perform are until the matrix is empty: 1. From each row, selec...
[ { "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 chemistry problem. It's a bit complex, but let's break it down step by step. First, I need to figure out the identities of the complexes X, Y, and Z. The problem mentions several reactions and properties, so let's parse them carefully. Starting with X: It's a pink aqueous solutio...
[ { "content": "Problem: The asymptotes of a hyperbola are $y = 2x - 3$ and $y = 17 - 2x.$ Also, the hyperbola passes through the point $(4,7).$ Find the distance between the foci of the hyperbola.\nMark your solution with \\boxed\nAnswer:", "role": "user" } ]
{ "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> Okay, so I need to find the distance between the foci of a hyperbola. The given asymptotes are y = 2x - 3 and y = 17 - 2x, and the hyperbola passes through the point (4,7). Hmm, let me start by recalling what I know about hyperbolas and their asymptotes. First, hyperbolas can be oriented either horizontally or...
[ { "content": "Problem: For how many integers $n$ does the expression\\[\\sqrt{\\frac{\\log (n^2) - (\\log n)^2}{\\log n - 3}}\\]represent a real number, where log denotes the base $10$ logarithm?\nMark your solution with \\boxed\nAnswer:", "role": "user" } ]
{ "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> Okay, so I need to figure out for how many integers \( n \) the expression \[ \sqrt{\frac{\log (n^2) - (\log n)^2}{\log n - 3}} \] represents a real number. The logarithm here is base 10. Let me start by breaking down the problem step by step. First, for the expression under the square root to be real, the ...
[{"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, let's see. I need to generate a Python function that finds all beautiful indices in (...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 }
"# Generated code\ndef generate_B():\n import sys\n input = sys.stdin.read\n data = input()(...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, so I need to write a Python function to solve this problem. Let me understand the pr(...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_science_fineweb_1744691386_eval_1331

Precomputed model outputs for evaluation.

Evaluation Results

Summary

Metric AIME24 AMC23 MATH500 GPQADiamond JEEBench MMLUPro LiveCodeBench CodeElo
Accuracy 16.3 53.0 76.2 39.2 35.3 28.8 17.2 2.9

AIME24

  • Average Accuracy: 16.33% ± 1.20%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 20.00% 6 30
2 16.67% 5 30
3 23.33% 7 30
4 10.00% 3 30
5 20.00% 6 30
6 16.67% 5 30
7 13.33% 4 30
8 13.33% 4 30
9 16.67% 5 30
10 13.33% 4 30

AMC23

  • Average Accuracy: 53.00% ± 1.96%
  • Number of Runs: 10
Run Accuracy Questions Solved Total Questions
1 57.50% 23 40
2 60.00% 24 40
3 57.50% 23 40
4 52.50% 21 40
5 45.00% 18 40
6 62.50% 25 40
7 42.50% 17 40
8 52.50% 21 40
9 52.50% 21 40
10 47.50% 19 40

MATH500

  • Accuracy: 76.20%
    Accuracy Questions Solved Total Questions
    76.20% 381 500

GPQADiamond

  • Average Accuracy: 39.23% ± 1.20%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 41.92% 83 198
2 36.87% 73 198
3 38.89% 77 198

JEEBench

  • Average Accuracy: 35.34% ± 0.55%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 35.58% 183.25 515
2 34.08% 175.5 515
3 36.36% 187.25 515

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: 17.16% ± 0.46%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 16.44% 84 511
2 18.00% 92 511
3 17.03% 87 511

CodeElo

  • Average Accuracy: 2.90% ± 0.47%
  • Number of Runs: 3
Run Accuracy Questions Solved Total Questions
1 2.30% 9 391
2 2.56% 10 391
3 3.84% 15 391
Downloads last month
3