feat(benchmark): smart-routing mode is the point — live results, per-model cost

The benchmark now leads with the product's actual feature. Two explicit modes: 🧭 Smart routing (default) — every probe goes through cortiq-auto; each row shows the router's task label judged against the expected one (✓/✗ with "expected: …"), the complexity tier, the chosen model with what that request cost, and a task-rule badge when a routing rule fired. KPIs: answer quality, classification accuracy, TTFT, tok/s and money spent, plus a "requests went to" distribution with per-model cost. 🎯 Individual models — the old head-to-head comparison, now as the clearly separate option (model checkboxes appear only here). The suite covers all 8 taxonomy labels (added summarization, creative-writing and chitchat probes; expected labels annotated per test). Results are LIVE: the table grows a row after every test (with a small fade-in), the progress card shows the prompt being asked, and a 🏁 verdict toast lands at the end with the score and the total spend. 12 new strings in all 7 languages.
2026-08-07 19:04:41 +03:00
parent 1120d8f11a
commit ec92bdddb7
9 changed files with 286 additions and 68 deletions
@@ -587,4 +587,18 @@ export default {
  "bm.addTest": "Test hinzufügen",
  "bm.emptyAnswer": "leere Antwort",
  "bm.loopDetected": "Schleife erkannt",
+
+  // benchmark: routing mode, cost, live
+  "bm.mode.routing": "Smartes Routing",
+  "bm.mode.models": "Einzelne Modelle",
+  "bm.mode.routingDesc": "Das Kernfeature des Produkts im Test: jede Probe läuft über cortiq-auto — Sie sehen, welche Aufgabe der Router erkannt hat, welches Modell er wählte, ob das den Erwartungen entspricht und was es gekostet hat.",
+  "bm.mode.modelsDesc": "Dieselbe Suite, an gewählte Modelle gepinnt — Qualität, Tempo und Kosten im direkten Vergleich, am Router vorbei.",
+  "bm.answersOk": "Antworten korrekt",
+  "bm.classAcc": "Aufgaben-Klassifikation",
+  "bm.modelDist": "Anfragen gingen an",
+  "bm.expectedLbl": "erwartet:",
+  "bm.answer": "Antwort",
+  "bm.liveRunning": "läuft…",
+  "bm.spent": "ausgegeben",
+  "bm.verdict": "🏁 Fertig: Antworten {p}, ausgegeben {s}",
 };
@@ -580,4 +580,18 @@ export default {
  "bm.addTest": "Add test",
  "bm.emptyAnswer": "empty answer",
  "bm.loopDetected": "loop detected",
+
+  // benchmark: routing mode, cost, live
+  "bm.mode.routing": "Smart routing",
+  "bm.mode.models": "Individual models",
+  "bm.mode.routingDesc": "The product's core feature under test: every probe goes through cortiq-auto — you see which task the router detected, which model it picked, whether that matches expectations, and what it cost.",
+  "bm.mode.modelsDesc": "The same suite pinned to selected models — compare their quality, speed and cost head-to-head, bypassing the router.",
+  "bm.answersOk": "answers correct",
+  "bm.classAcc": "task classification",
+  "bm.modelDist": "Requests went to",
+  "bm.expectedLbl": "expected:",
+  "bm.answer": "Answer",
+  "bm.liveRunning": "running…",
+  "bm.spent": "spent",
+  "bm.verdict": "🏁 Done: answers {p}, spent {s}",
 };
@@ -587,4 +587,18 @@ export default {
  "bm.addTest": "Añadir prueba",
  "bm.emptyAnswer": "respuesta vacía",
  "bm.loopDetected": "bucle detectado",
+
+  // benchmark: routing mode, cost, live
+  "bm.mode.routing": "Enrutado inteligente",
+  "bm.mode.models": "Modelos individuales",
+  "bm.mode.routingDesc": "La función clave del producto a prueba: cada sonda pasa por cortiq-auto — ves qué tarea detectó el router, qué modelo eligió, si coincide con lo esperado y cuánto costó.",
+  "bm.mode.modelsDesc": "La misma suite fijada a los modelos elegidos — compara su calidad, velocidad y coste directamente, sin pasar por el router.",
+  "bm.answersOk": "respuestas correctas",
+  "bm.classAcc": "clasificación de tareas",
+  "bm.modelDist": "Las peticiones fueron a",
+  "bm.expectedLbl": "esperado:",
+  "bm.answer": "Respuesta",
+  "bm.liveRunning": "en curso…",
+  "bm.spent": "gastado",
+  "bm.verdict": "🏁 Listo: respuestas {p}, gastado {s}",
 };
@@ -587,4 +587,18 @@ export default {
  "bm.addTest": "Ajouter un test",
  "bm.emptyAnswer": "réponse vide",
  "bm.loopDetected": "boucle détectée",
+
+  // benchmark: routing mode, cost, live
+  "bm.mode.routing": "Routage intelligent",
+  "bm.mode.models": "Modèles individuels",
+  "bm.mode.routingDesc": "La fonctionnalité clé du produit à l'épreuve : chaque sonde passe par cortiq-auto — vous voyez quelle tâche le routeur a détectée, quel modèle il a choisi, si cela correspond aux attentes et combien cela a coûté.",
+  "bm.mode.modelsDesc": "La même suite épinglée aux modèles choisis — comparez leur qualité, vitesse et coût en direct, sans passer par le routeur.",
+  "bm.answersOk": "réponses correctes",
+  "bm.classAcc": "classification des tâches",
+  "bm.modelDist": "Requêtes envoyées vers",
+  "bm.expectedLbl": "attendu :",
+  "bm.answer": "Réponse",
+  "bm.liveRunning": "en cours…",
+  "bm.spent": "dépensé",
+  "bm.verdict": "🏁 Terminé : réponses {p}, dépensé {s}",
 };
@@ -579,4 +579,18 @@ export default {
  "bm.addTest": "Добавить тест",
  "bm.emptyAnswer": "пустой ответ",
  "bm.loopDetected": "зацикливание",
+
+  // benchmark: routing mode, cost, live
+  "bm.mode.routing": "Умный роутинг",
+  "bm.mode.models": "Отдельные модели",
+  "bm.mode.routingDesc": "Проверка главной фишки продукта: каждый тест идёт через cortiq-auto — видно, какую задачу распознал роутер, какую модель выбрал, совпало ли это с ожиданием и сколько это стоило.",
+  "bm.mode.modelsDesc": "Тот же набор тестов, но закреплённый за выбранными моделями — сравнение их качества, скорости и стоимости напрямую, мимо роутера.",
+  "bm.answersOk": "ответы верны",
+  "bm.classAcc": "классификация задач",
+  "bm.modelDist": "Запросы ушли в",
+  "bm.expectedLbl": "ожидалось:",
+  "bm.answer": "Ответ",
+  "bm.liveRunning": "идёт…",
+  "bm.spent": "потрачено",
+  "bm.verdict": "🏁 Готово: ответы {p}, потрачено {s}",
 };
@@ -587,4 +587,18 @@ export default {
  "bm.addTest": "Test ekle",
  "bm.emptyAnswer": "boş yanıt",
  "bm.loopDetected": "döngü tespit edildi",
+
+  // benchmark: routing mode, cost, live
+  "bm.mode.routing": "Akıllı yönlendirme",
+  "bm.mode.models": "Tek tek modeller",
+  "bm.mode.routingDesc": "Ürünün temel özelliği testte: her prob cortiq-auto üzerinden gider — yönlendiricinin hangi görevi algıladığını, hangi modeli seçtiğini, bunun beklentiyle örtüşüp örtüşmediğini ve maliyetini görürsünüz.",
+  "bm.mode.modelsDesc": "Aynı küme seçilen modellere sabitlenir — yönlendiriciyi atlayarak kalite, hız ve maliyeti doğrudan karşılaştırın.",
+  "bm.answersOk": "yanıtlar doğru",
+  "bm.classAcc": "görev sınıflandırması",
+  "bm.modelDist": "İstekler şuraya gitti",
+  "bm.expectedLbl": "beklenen:",
+  "bm.answer": "Yanıt",
+  "bm.liveRunning": "sürüyor…",
+  "bm.spent": "harcanan",
+  "bm.verdict": "🏁 Bitti: yanıtlar {p}, harcanan {s}",
 };
@@ -587,4 +587,18 @@ export default {
  "bm.addTest": "添加测试",
  "bm.emptyAnswer": "回答为空",
  "bm.loopDetected": "检测到循环",
+
+  // benchmark: routing mode, cost, live
+  "bm.mode.routing": "智能路由",
+  "bm.mode.models": "单独模型",
+  "bm.mode.routingDesc": "测试产品核心能力：每个探测都经过 cortiq-auto — 可以看到路由器识别的任务、选中的模型、是否符合预期，以及花费了多少。",
+  "bm.mode.modelsDesc": "同一套测试固定在所选模型上 — 绕过路由器，直接对比它们的质量、速度与成本。",
+  "bm.answersOk": "回答正确",
+  "bm.classAcc": "任务分类",
+  "bm.modelDist": "请求流向",
+  "bm.expectedLbl": "预期：",
+  "bm.answer": "回答",
+  "bm.liveRunning": "进行中……",
+  "bm.spent": "花费",
+  "bm.verdict": "🏁 完成：回答 {p}，花费 {s}",
 };