Qwen3-0.6B-Math-Surgery-v2 / benchmark_problems.py
zerolimites's picture
Upload Qwen3-0.6B-Math-Surgery-v2 (76.67% (23/30, 0 regressions) - Safetensors + GGUF Q8_0 & F16 + JSONs)
f848473 verified
Raw History Blame Contribute Delete
6.78 kB
# Benchmark de Matemática para Avaliação do Qwen3-0.6B (30 Questões Verificadas)
# Dividido em 4 categorias:
# 1. Aritmética Multi-etapas (8 questões)
# 2. Problemas Contextualizados / GSM8K-style (8 questões)
# 3. Álgebra & Equações (7 questões)
# 4. Teoria dos Números, Combinatória & Geometria (7 questões)
BENCHMARK_PROBLEMS = [
# --- 1. Aritmética Multi-etapas ---
{
"id": "ARITH_01",
"category": "Arithmetic",
"question": "Calculate: 17 * 24 - 19.",
"answer": "389"
},
{
"id": "ARITH_02",
"category": "Arithmetic",
"question": "Calculate: (145 + 235) / 5 + 18 * 3.",
"answer": "130"
},
{
"id": "ARITH_03",
"category": "Arithmetic",
"question": "Calculate: 23 * 19 - 14 * 12.",
"answer": "269"
},
{
"id": "ARITH_04",
"category": "Arithmetic",
"question": "Calculate: 360 / 15 + 27 * 4 - 39.",
"answer": "93"
},
{
"id": "ARITH_05",
"category": "Arithmetic",
"question": "Calculate: 16 * 16 + 15 * 15 - 14 * 14.",
"answer": "285"
},
{
"id": "ARITH_06",
"category": "Arithmetic",
"question": "Calculate: (84 - 29) * 6 - 115.",
"answer": "215"
},
{
"id": "ARITH_07",
"category": "Arithmetic",
"question": "Calculate: 42 * 13 - 28 * 9.",
"answer": "294"
},
{
"id": "ARITH_08",
"category": "Arithmetic",
"question": "Calculate: 125 * 8 - 37 * 11.",
"answer": "593"
},
# --- 2. Problemas Contextualizados (GSM8K-style) ---
{
"id": "GSM_01",
"category": "Word Problems (GSM8K)",
"question": "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May?",
"answer": "72"
},
{
"id": "GSM_02",
"category": "Word Problems (GSM8K)",
"question": "A store sells apples for 3 dollars each and oranges for 4 dollars each. If John buys 5 apples and 6 oranges, and pays with a 50 dollar bill, how many dollars of change does he get?",
"answer": "11"
},
{
"id": "GSM_03",
"category": "Word Problems (GSM8K)",
"question": "A train travels at 60 km/h for 2 hours, then at 75 km/h for 4 hours. What is the total distance traveled in km?",
"answer": "420"
},
{
"id": "GSM_04",
"category": "Word Problems (GSM8K)",
"question": "A bakery makes 120 muffins every morning. They sell 45 muffins before noon and 38 muffins in the afternoon. If they pack the remaining muffins into boxes of 5, how many muffins are left unpacked?",
"answer": "2"
},
{
"id": "GSM_05",
"category": "Word Problems (GSM8K)",
"question": "Sarah reads 18 pages of a book each day for 6 days, and then reads 25 pages each day for the next 4 days. If the book has 250 pages in total, how many pages does she still have left to read?",
"answer": "42"
},
{
"id": "GSM_06",
"category": "Word Problems (GSM8K)",
"question": "A factory produces 35 toys per hour. It operates for 8 hours a day. Over 5 days, 40 toys fail inspection and are discarded. How many good toys are produced in those 5 days?",
"answer": "1360"
},
{
"id": "GSM_07",
"category": "Word Problems (GSM8K)",
"question": "Mark has 3 times as many marbles as Lucas. Lucas has 14 more marbles than Leo. If Leo has 12 marbles, how many marbles do Mark and Lucas have together?",
"answer": "104"
},
{
"id": "GSM_08",
"category": "Word Problems (GSM8K)",
"question": "A jacket originally costs 160 dollars. It is on sale for 25% off, and a customer also uses a 15 dollar coupon after the percentage discount. What is the final price in dollars?",
"answer": "105"
},
# --- 3. Álgebra & Equações ---
{
"id": "ALG_01",
"category": "Algebra",
"question": "Solve for x: 7x - 19 = 3x + 29. What is x?",
"answer": "12"
},
{
"id": "ALG_02",
"category": "Algebra",
"question": "If 2x + 3y = 31 and x - y = 3, what is the value of x + y?",
"answer": "11"
},
{
"id": "ALG_03",
"category": "Algebra",
"question": "The sum of three consecutive integers is 114. What is the largest of these three integers?",
"answer": "39"
},
{
"id": "ALG_04",
"category": "Algebra",
"question": "If f(x) = 3x^2 - 5x + 4, what is the value of f(6)?",
"answer": "82"
},
{
"id": "ALG_05",
"category": "Algebra",
"question": "Solve for x: 4(2x - 3) = 3(x + 6) + 5. What is x?",
"answer": "7"
},
{
"id": "ALG_06",
"category": "Algebra",
"question": "The sum of two numbers is 45 and their difference is 13. What is the product of the two numbers?",
"answer": "464"
},
{
"id": "ALG_07",
"category": "Algebra",
"question": "If a + b = 11 and a^2 + b^2 = 65, what is the value of a * b?",
"answer": "28"
},
# --- 4. Teoria dos Números, Combinatória & Geometria ---
{
"id": "NTG_01",
"category": "Number Theory & Geometry",
"question": "A rectangle has a perimeter of 54 cm and a length of 16 cm. What is its area in square cm?",
"answer": "176"
},
{
"id": "NTG_02",
"category": "Number Theory & Geometry",
"question": "What is the remainder when 2^9 is divided by 7?",
"answer": "1"
},
{
"id": "NTG_03",
"category": "Number Theory & Geometry",
"question": "A right triangle has legs of length 9 and 12. What is its perimeter?",
"answer": "36"
},
{
"id": "NTG_04",
"category": "Number Theory & Geometry",
"question": "How many positive divisors does the number 72 have?",
"answer": "12"
},
{
"id": "NTG_05",
"category": "Number Theory & Geometry",
"question": "What is the sum of the first 25 positive integers (1 + 2 + 3 + ... + 25)?",
"answer": "325"
},
{
"id": "NTG_06",
"category": "Number Theory & Geometry",
"question": "In how many ways can a committee of 3 people be chosen from a group of 8 people?",
"answer": "56"
},
{
"id": "NTG_07",
"category": "Number Theory & Geometry",
"question": "What is the greatest common divisor (GCD) of 144 and 210?",
"answer": "6"
},
]