Consistency Fix: Filter new leaderboard_math_hard dataset to "Level 5" only (#2773)

* Filter new leaderboard_math_hard dataset to "Level 5" only

* align to linters
Signed-off-by: Yotam Perlitz <y.perlitz@ibm.com>

---------
Signed-off-by: Yotam Perlitz <y.perlitz@ibm.com>

lm_eval/tasks/leaderboard/math/utils.py

@@ -17,7 +17,6 @@ except ModuleNotFoundError:
 please install sympy via pip install lm-eval[math] or pip install -e .[math]",
     )
 
-
 INVALID_ANSWER = "[invalidanswer]"
 
 
@@ -40,7 +39,7 @@ def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:
             out_doc["few_shot"] = True
         return out_doc
 
-    return dataset.map(_process_doc)
+    return dataset.filter(lambda x: x["level"] == "Level 5").map(_process_doc)
 
 
 def list_fewshot_samples() -> list[dict]:
@@ -49,21 +48,25 @@ def list_fewshot_samples() -> list[dict]:
             "problem": "Find the domain of the expression  $\\frac{\\sqrt{x-2}}{\\sqrt{5-x}}$.}",
             "solution": "The expressions inside each square root must be non-negative. Therefore, $x-2 \\ge 0$, so $x\\ge2$, and $5 - x \\ge 0$, so $x \\le 5$. Also, the denominator cannot be equal to zero, so $5-x>0$, which gives $x<5$. Therefore, the domain of the expression is $\\boxed{[2,5)}$.\nFinal Answer: The final answer is $[2,5)$. I hope it is correct.",
             "few_shot": "1",
+            "level": "Level 5",
         },
         {
             "problem": "If $\\det \\mathbf{A} = 2$ and $\\det \\mathbf{B} = 12,$ then find $\\det (\\mathbf{A} \\mathbf{B}).$",
             "solution": "We have that $\\det (\\mathbf{A} \\mathbf{B}) = (\\det \\mathbf{A})(\\det \\mathbf{B}) = (2)(12) = \\boxed{24}.$\nFinal Answer: The final answer is $24$. I hope it is correct.",
             "few_shot": "1",
+            "level": "Level 5",
         },
         {
             "problem": "Terrell usually lifts two 20-pound weights 12 times. If he uses two 15-pound weights instead, how many times must Terrell lift them in order to lift the same total weight?",
             "solution": "If Terrell lifts two 20-pound weights 12 times, he lifts a total of $2\\cdot 12\\cdot20=480$ pounds of weight.  If he lifts two 15-pound weights instead for $n$ times, he will lift a total of $2\\cdot15\\cdot n=30n$ pounds of weight.  Equating this to 480 pounds, we can solve for $n$:\n\\begin{align*}\n30n&=480\\\n\\Rightarrow\\qquad n&=480/30=\\boxed{16}\n\\end{align*}\nFinal Answer: The final answer is $16$. I hope it is correct.",
             "few_shot": "1",
+            "level": "Level 5",
         },
         {
             "problem": "If the system of equations\n\n\\begin{align*}\n6x-4y&=a,\\\n6y-9x &=b.\n\\end{align*}has a solution $(x, y)$ where $x$ and $y$ are both nonzero,\nfind $\\frac{a}{b},$ assuming $b$ is nonzero.",
             "solution": "If we multiply the first equation by $-\\frac{3}{2}$, we obtain\n\n$$6y-9x=-\\frac{3}{2}a.$$Since we also know that $6y-9x=b$, we have\n\n$$-\\frac{3}{2}a=b\\Rightarrow\\frac{a}{b}=\\boxed{-\\frac{2}{3}}.$$\nFinal Answer: The final answer is $-\\frac{2}{3}$. I hope it is correct.",
             "few_shot": "1",
+            "level": "Level 5",
         },
     ]