feat(bench): real-song benchmark

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

src/eval/score.ts

@@ -30,12 +30,12 @@ export const DRUM_CLASSES: Record<DrumClass, number[]> = {
 };
 const PASS_F1 = 0.85;
 
-function drumClass(pitch: number): DrumClass | null {
+export function drumClass(pitch: number): DrumClass | null {
   for (const [c, ps] of Object.entries(DRUM_CLASSES)) if (ps.includes(pitch)) return c as DrumClass;
   return null;
 }
 // Drum pitches are compared by class: map to the class's first GM number; unknown pitches stay distinct.
-const toClassPitch = (n: TimedNote): TimedNote => {
+export const toClassPitch = (n: TimedNote): TimedNote => {
   const c = drumClass(n.pitch);
   return { ...n, pitch: c ? DRUM_CLASSES[c][0]! : 1000 + n.pitch };
 };