feat: writing effective tools

This commit is contained in:
Ken Aizawa
2025-09-10 23:43:39 +00:00
parent afb6dad5dc
commit e9bb3e1008
2 changed files with 1359 additions and 0 deletions

View File

@@ -0,0 +1,116 @@
<evaluation>
<!-- Date/Time Calculations -->
<task>
<prompt>How many days are between March 15, 2024 and September 22, 2025? Include both start and end dates in your count.</prompt>
<response>557</response>
</task>
<task>
<prompt>If a meeting starts at 11:45 AM and lasts for 2 hours and 37 minutes, what time does it end? Express in 24-hour format as HH:MM.</prompt>
<response>14:22</response>
</task>
<!-- Modular Arithmetic -->
<task>
<prompt>What is 2^100 mod 7? Give the exact integer result.</prompt>
<response>2</response>
</task>
<task>
<prompt>What day of the week will it be 1000 days from Monday?</prompt>
<response>Wednesday</response>
</task>
<!-- Factorial/Combinatorics -->
<task>
<prompt>Calculate 15! (15 factorial). Give the exact integer result.</prompt>
<response>1307674368000</response>
</task>
<task>
<prompt>How many different ways can you choose 5 items from a set of 12 items? (Calculate C(12,5))</prompt>
<response>792</response>
</task>
<!-- Trigonometric Functions -->
<task>
<prompt>Calculate sin(π/6) + cos(π/3) + tan(π/4). Give the exact value.</prompt>
<response>2</response>
</task>
<!-- Logarithms/Exponentials -->
<task>
<prompt>Solve for x: 2^x = 128. Give the exact integer value.</prompt>
<response>7</response>
</task>
<task>
<prompt>Calculate ln(e^3) + log₁₀(1000) - log₂(8). Give the exact value.</prompt>
<response>3</response>
</task>
<!-- Matrix Operations -->
<task>
<prompt>Calculate the determinant of the 2x2 matrix [[3, 7], [2, 5]].</prompt>
<response>1</response>
</task>
<!-- Number Theory -->
<task>
<prompt>What is the greatest common divisor (GCD) of 1071 and 462?</prompt>
<response>21</response>
</task>
<task>
<prompt>Is 97 a prime number? Answer 'true' or 'false'.</prompt>
<response>true</response>
</task>
<!-- Bitwise Operations -->
<task>
<prompt>Calculate 42 XOR 15 (bitwise exclusive OR).</prompt>
<response>37</response>
</task>
<!-- Floor/Ceiling Functions -->
<task>
<prompt>Calculate floor(7.8) × ceiling(2.1) + round(4.5).</prompt>
<response>25</response>
</task>
<!-- Complex Numbers -->
<task>
<prompt>Calculate the magnitude of the complex number 3 + 4i.</prompt>
<response>5</response>
</task>
<!-- Base Conversions -->
<task>
<prompt>Convert the hexadecimal number FF to decimal.</prompt>
<response>255</response>
</task>
<!-- Statistical Functions -->
<task>
<prompt>Calculate the median of this dataset: [3, 7, 2, 9, 1, 5, 8].</prompt>
<response>5</response>
</task>
<!-- Recursive Calculations -->
<task>
<prompt>Calculate the 10th Fibonacci number (where F(1)=1, F(2)=1).</prompt>
<response>55</response>
</task>
<!-- Percentage of Percentage -->
<task>
<prompt>What is 25% of 40% of 80% of 500?</prompt>
<response>40</response>
</task>
<!-- Unit Conversions -->
<task>
<prompt>Convert 72 degrees Fahrenheit to Celsius. Round to 1 decimal place.</prompt>
<response>22.2</response>
</task>
</evaluation>

File diff suppressed because it is too large Load Diff