|
| 1 | +benchmarks = [ |
| 2 | + { |
| 3 | + "response": "2a", |
| 4 | + "answer": "a", |
| 5 | + "params": { |
| 6 | + "strict_syntax": False, |
| 7 | + "elementary_functions": True, |
| 8 | + "criteria": "response/answer=2", |
| 9 | + } |
| 10 | + }, |
| 11 | + { |
| 12 | + "response": "2*x**2 = 10*y**2+20", |
| 13 | + "answer": "x**2-5*y**2-10=0", |
| 14 | + "params": {"strict_syntax": False} |
| 15 | + }, |
| 16 | + { |
| 17 | + "response": "1.24 mile/hour", |
| 18 | + "answer": "1.24 mile/hour", |
| 19 | + "params": { |
| 20 | + "strict_syntax": False, |
| 21 | + "elementary_functions": True, |
| 22 | + "physical_quantity": True, |
| 23 | + } |
| 24 | + }, |
| 25 | + { |
| 26 | + "response": "sin(x)+2", |
| 27 | + "answer": "sin(x)", |
| 28 | + "params": { |
| 29 | + "strict_syntax": False, |
| 30 | + "elementary_functions": True, |
| 31 | + "criteria": "Derivative(response,x)=cos(x)", |
| 32 | + } |
| 33 | + }, |
| 34 | + { |
| 35 | + "response": "cos(x)**2 + sin(x)**2 + y", |
| 36 | + "answer": "y + 1", |
| 37 | + "params": {"strict_syntax": False} |
| 38 | + }, |
| 39 | + { |
| 40 | + "response": "log(2)/2+I*(3*pi/4 plus_minus 2*n*pi)", |
| 41 | + "answer": "log(2)/2+I*(3*pi/4 plus_minus 2*n*pi)", |
| 42 | + "params": { |
| 43 | + "strict_syntax": False, |
| 44 | + "elementary_functions": True, |
| 45 | + } |
| 46 | + }, |
| 47 | + { |
| 48 | + "response": "6*cos(5*x+1)-90*x*sin(5*x+1)-225*x**2*cos(5*x+1)+125*x**3*sin(5*x+1)", |
| 49 | + "answer": "6*cos(5*x+1)-90*x*sin(5*x+1)-225*x**2*cos(5*x+1)+125*x**3*sin(5*x+1)", |
| 50 | + "params": {"strict_syntax": False} |
| 51 | + }, |
| 52 | + { |
| 53 | + "response": "-(sin(xy)y+(e^y))/(x(e^y+sin(xy)x))", |
| 54 | + "answer": "-(y*sin(x*y) + e^(y)) / (x*(e^(y) + sin(x*y)))", |
| 55 | + "params": {"strict_syntax": False} |
| 56 | + }, |
| 57 | +] |
0 commit comments