Update benchmarks with LoRA-bev-v9 results (May 2026)

index.html

@@ -329,7 +329,7 @@ const SECTIONS = [
       {
         title: "Synonym Recognition",
         metric: "Recall@5",
-        scores: { dish_embed: 0.808, openai: 0.749, bge_m3: 0.707, qwen3: 0.514, e5_large: 0.661 }
+        scores: { dish_embed: 0.835, openai: 0.749, bge_m3: 0.707, qwen3: 0.514, e5_large: 0.661 }
       },
       {
         title: "Cuisine Classification (19 cuisines)",
@@ -346,22 +346,22 @@ const SECTIONS = [
       {
         title: "Category Search",
         metric: "NDCG@10",
-        scores: { dish_embed: 0.828, openai: 0.797, bge_m3: 0.759, qwen3: 0.802, e5_large: 0.799 }
+        scores: { dish_embed: 0.856, openai: 0.797, bge_m3: 0.759, qwen3: 0.802, e5_large: 0.799 }
       },
       {
         title: "Typo-Tolerant Search",
         metric: "NDCG@10",
-        scores: { dish_embed: 0.920, openai: 0.884, bge_m3: 0.902, qwen3: 0.892, e5_large: 0.907 }
+        scores: { dish_embed: 0.910, openai: 0.884, bge_m3: 0.902, qwen3: 0.892, e5_large: 0.907 }
       },
       {
         title: "Food Search",
         metric: "NDCG@10",
-        scores: { dish_embed: 0.943, openai: 0.925, bge_m3: 0.929, qwen3: 0.935, e5_large: 0.939 }
+        scores: { dish_embed: 0.944, openai: 0.925, bge_m3: 0.929, qwen3: 0.935, e5_large: 0.939 }
       },
       {
         title: "Global Search",
         metric: "NDCG@10",
-        scores: { dish_embed: 0.891, openai: 0.839, bge_m3: 0.886, qwen3: 0.875, e5_large: 0.860 }
+        scores: { dish_embed: 0.900, openai: 0.839, bge_m3: 0.886, qwen3: 0.875, e5_large: 0.860 }
       }
     ]
   },
@@ -374,22 +374,22 @@ const SECTIONS = [
       {
         title: "Indian Cuisine Matching",
         metric: "F1",
-        scores: { dish_embed: 0.916, off_shelf: 0.754 }
+        scores: { dish_embed: 0.919, off_shelf: 0.754 }
       },
       {
         title: "Cross-Language Matching",
         metric: "F1",
-        scores: { dish_embed: 0.831, off_shelf: 0.258 }
+        scores: { dish_embed: 0.844, off_shelf: 0.258 }
       },
       {
         title: "Bakery & Dessert Matching",
         metric: "F1",
-        scores: { dish_embed: 0.797, off_shelf: 0.655 }
+        scores: { dish_embed: 0.783, off_shelf: 0.655 }
       },
       {
         title: "Beverage Matching",
         metric: "F1",
-        scores: { dish_embed: 0.747, off_shelf: 0.648 }
+        scores: { dish_embed: 0.744, off_shelf: 0.648 }
       },
     ]
   },
@@ -402,19 +402,19 @@ const SECTIONS = [
         title: "Portion Size Sensitivity",
         metric: "F1",
         mode: "collapsed",
-        scores: { dish_embed: 0.877, off_shelf: 0.082 }
+        scores: { dish_embed: 0.885, off_shelf: 0.082 }
       },
       {
         title: "Noisy Menu Matching",
         metric: "F1",
         mode: "collapsed",
-        scores: { dish_embed: 0.922, off_shelf: 0.914 }
+        scores: { dish_embed: 0.926, off_shelf: 0.914 }
       },
       {
         title: "Bilingual Menu Matching",
         metric: "F1",
         mode: "collapsed",
-        scores: { dish_embed: 0.886, off_shelf: 0.879 }
+        scores: { dish_embed: 0.907, off_shelf: 0.879 }
       },
       {
         title: "Embedding Stability",