github/cortiq-gateway
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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.
This commit is contained in:
infosave2007
2026-08-07 19:04:41 +03:00
parent 1120d8f11a
commit ec92bdddb7
9 changed files with 286 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files
web/css/styles.css
Vendored
+2
View File
@@ -586,6 +586,8 @@ body.modal-open { overflow: hidden; }
room than the search grid before it starts scrolling. */
.featured-section .hf-grid { max-height: min(62vh, 760px); }
/* Benchmark view */
@keyframes bm-in { from { opacity: 0; transform: translateY(-3px); } to { opacity: 1; transform: none; } }
tbody tr:last-child { animation: bm-in .25s ease; }
.bm-sum { margin-bottom: 10px; }
.bm-cell { cursor: pointer; white-space: nowrap; }
.bm-cell:hover { background: var(--hover); }
web/js/i18n/de.js
Vendored
+14
View File
@@ -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}",
};
web/js/i18n/en.js
Vendored
+14
View File
@@ -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}",
};
web/js/i18n/es.js
Vendored
+14
View File
@@ -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}",
};
web/js/i18n/fr.js
Vendored
+14
View File
@@ -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}",
};
web/js/i18n/ru.js
Vendored
+14
View File
@@ -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}",
};
web/js/i18n/tr.js
Vendored
+14
View File
@@ -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}",
};
web/js/i18n/zh.js
Vendored
+14
View File
@@ -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}",
};
web/js/views/benchmark.js
Vendored
+186 -68
View File
@@ -1,9 +1,13 @@
// Benchmark — quality + speed probes for pool models, run through the live
// pipeline (pinned per model, streaming → TTFT and tok/s are real).
// Benchmark — two modes over the live pipeline:
// 🧭 Smart routing (default): the product's core promise under test — every
// probe goes through cortiq-auto and the router's task/tier decision and
// chosen model are judged alongside the answer itself.
// 🎯 Individual models: the same suite pinned to selected models — compare
// quality and speed head-to-head.
// A redesign of the old standalone benchmark.html: same scoring ideas
// (keyword checks with | synonyms, think-tag stripping, anti-loop detection,
// pass/partial/fail), now embedded, localized and CDN-free.
import { h, mount, toast, ms } from "../ui.js";
import { h, mount, toast, ms, money } from "../ui.js";
import { t } from "../i18n.js";
import { api, testStream } from "../api.js";
@@ -11,19 +15,24 @@ import { api, testStream } from "../api.js";
// Checks are language-neutral where possible (digits, identifiers, emails);
// `check` entries may hold |-separated synonyms — one hit per entry counts.
// `quick: true` marks the fast subset.
// `label`: router task labels accepted as a correct classification (null = not
// judged — the prompt has no natural label in the taxonomy).
const SUITE = [
{ id: "math-mult", cat: "math", quick: true, max: 96, prompt: "What is 17 * 23? Answer with the number only.", check: ["391"] },
{ id: "math-eq", cat: "math", max: 128, prompt: "Solve 2x + 6 = 14. Answer with the value of x only.", check: ["4"] },
{ id: "logic-syll", cat: "logic", max: 96, prompt: "If all bloops are razzies and all razzies are lazzies, are all bloops lazzies? Answer yes or no.", check: ["yes|да|oui|ja|sí|si|evet|是"] },
{ id: "count-letters", cat: "logic", quick: true, max: 64, prompt: "How many letters are in the word 'cat'? Answer with a digit.", check: ["3"] },
{ id: "apples", cat: "logic", quick: true, max: 96, prompt: "John has 3 apples, buys 2 more, then eats 1. How many apples does he have? Answer with a digit.", check: ["4"] },
{ id: "code-fact", cat: "code", max: 256, prompt: "Write a Python function factorial(n) that returns n!.", check: ["def", "factorial", "return"] },
{ id: "qa-capital", cat: "qa", quick: true, max: 48, prompt: "What is the capital of France? One word.", check: ["paris|париж"] },
{ id: "primes", cat: "qa", max: 96, prompt: "List the first five prime numbers, comma-separated.", check: ["2", "3", "5", "7", "11"] },
{ id: "instr-ok", cat: "instruction", quick: true, max: 32, prompt: "Reply with exactly the word OK and nothing else.", check: ["ok"] },
{ id: "extract-email", cat: "extraction", quick: true, max: 64, prompt: "Extract the email address from: 'Contact us at info@example.com today.' Reply with the address only.", check: ["info@example.com"] },
{ id: "translate", cat: "translation", max: 64, prompt: "Translate to English: «Доброе утро». Reply with the translation only.", check: ["good morning"] },
{ id: "format-json", cat: "instruction", max: 96, prompt: 'Return a JSON object with a single key "n" whose value is 7. JSON only.', check: ['"n"', "7"] },
{ id: "math-mult", cat: "math", label: ["math"], quick: true, max: 96, prompt: "What is 17 * 23? Answer with the number only.", check: ["391"] },
{ id: "math-eq", cat: "math", label: ["math"], max: 128, prompt: "Solve 2x + 6 = 14. Answer with the value of x only.", check: ["4"] },
{ id: "logic-syll", cat: "logic", label: ["qa", "math"], max: 96, prompt: "If all bloops are razzies and all razzies are lazzies, are all bloops lazzies? Answer yes or no.", check: ["yes|да|oui|ja|sí|si|evet|是"] },
{ id: "count-letters", cat: "logic", label: ["qa", "math"], quick: true, max: 64, prompt: "How many letters are in the word 'cat'? Answer with a digit.", check: ["3"] },
{ id: "apples", cat: "logic", label: ["math", "qa"], quick: true, max: 96, prompt: "John has 3 apples, buys 2 more, then eats 1. How many apples does he have? Answer with a digit.", check: ["4"] },
{ id: "code-fact", cat: "code", label: ["code"], max: 256, prompt: "Write a Python function factorial(n) that returns n!.", check: ["def", "factorial", "return"] },
{ id: "qa-capital", cat: "qa", label: ["qa"], quick: true, max: 48, prompt: "What is the capital of France? One word.", check: ["paris|париж"] },
{ id: "primes", cat: "qa", label: ["math", "qa"], max: 96, prompt: "List the first five prime numbers, comma-separated.", check: ["2", "3", "5", "7", "11"] },
{ id: "instr-ok", cat: "instruction", label: null, quick: true, max: 32, prompt: "Reply with exactly the word OK and nothing else.", check: ["ok"] },
{ id: "extract-email", cat: "extraction", label: ["extraction"], quick: true, max: 64, prompt: "Extract the email address from: 'Contact us at info@example.com today.' Reply with the address only.", check: ["info@example.com"] },
{ id: "translate", cat: "translation", label: ["translation"], max: 64, prompt: "Translate to English: «Доброе утро». Reply with the translation only.", check: ["good morning"] },
{ id: "format-json", cat: "instruction", label: null, max: 96, prompt: 'Return a JSON object with a single key "n" whose value is 7. JSON only.', check: ['"n"', "7"] },
{ id: "summarize", cat: "summarization", label: ["summarization"], max: 96, prompt: "Summarize in one short sentence: 'The cat sat on the warm mat by the window. After a while it curled up and fell asleep in the sun.'", check: ["cat|кот|кошк"] },
{ id: "creative", cat: "creative-writing", label: ["creative-writing"], max: 96, prompt: "Write a two-line poem about the sea.", check: ["sea|море|ocean"] },
{ id: "chitchat", cat: "chitchat", label: ["chitchat"], quick: true, max: 48, prompt: "Hi! How are you today?", check: [] },
];
const LS_CUSTOM = "allaigate_bench_custom";
@@ -71,6 +80,7 @@ function evaluate(raw, test) {
const resp = text.toLowerCase();
if (!resp.trim()) return { status: "fail", score: 0, note: t("bm.emptyAnswer") };
if (looksLooped(resp)) return { status: "fail", score: 0, note: t("bm.loopDetected") };
if (!test.check.length) return { status: "pass", score: 1, note: "✓" };
let hit = 0;
for (const cond of test.check) {
const opts = cond.toLowerCase().split("|").map((s) => s.trim());
@@ -88,12 +98,27 @@ export async function renderBenchmark() {
let running = false;
let stopFlag = false;
let mode = "routing"; // routing (cortiq-auto, the product's feature) | models
const modelCbs = ids.map((id) => ({ id, cb: h("input", { type: "checkbox", checked: ids.length === 1 ? true : null }) }));
const quickCb = h("input", { type: "checkbox", checked: true });
const resultsHost = h("div", {});
const progressHost = h("div", {});
const historyHost = h("div", {});
const modeDesc = h("p", { class: "muted", style: "margin:8px 0 0" }, t("bm.mode.routingDesc"));
const modelsPick = h("div", { class: "flex wrap", style: "gap:10px; margin-top:12px; display:none" },
...modelCbs.map(({ id, cb }) => h("label", { class: "check" }, cb, h("span", { class: "mono" }, id))));
const modeSeg = h("div", { class: "seg" },
h("button", { class: "active" }, "🧭 " + t("bm.mode.routing")),
h("button", {}, "🎯 " + t("bm.mode.models")));
modeSeg.querySelectorAll("button").forEach((b, i) =>
b.addEventListener("click", () => {
mode = i === 0 ? "routing" : "models";
modeSeg.querySelectorAll("button").forEach((x, j) => x.classList.toggle("active", j === i));
modelsPick.style.display = mode === "models" ? "" : "none";
modeDesc.textContent = t(mode === "routing" ? "bm.mode.routingDesc" : "bm.mode.modelsDesc");
}));
function suite() {
const base = SUITE.concat(customTests());
return quickCb.checked ? base.filter((x) => x.quick || x.custom) : base;
@@ -107,7 +132,7 @@ export async function renderBenchmark() {
});
runBtn.addEventListener("click", async () => {
const models = modelCbs.filter((m) => m.cb.checked).map((m) => m.id);
const models = mode === "routing" ? ["cortiq-auto"] : modelCbs.filter((m) => m.cb.checked).map((m) => m.id);
if (!models.length) {
toast(t("bm.pickModel"), "warn");
return;
@@ -118,7 +143,7 @@ export async function renderBenchmark() {
stopBtn.style.display = "";
stopBtn.disabled = false;
const tests = suite();
const run = { ts: Date.now(), quick: quickCb.checked, models: {}, nTests: tests.length };
const run = { ts: Date.now(), mode, quick: quickCb.checked, models: {}, nTests: tests.length };
for (const model of models) {
const rec = { results: [], score: 0, tokS: [], ttft: [], failed: false };
@@ -131,9 +156,10 @@ export async function renderBenchmark() {
h("div", { class: "card" },
h("div", { class: "flex" },
h("span", { class: "spinner" }), " ",
h("b", { class: "mono" }, model), " · ",
h("b", { class: "mono" }, mode === "routing" ? t("bm.mode.routing") : model), " · ",
t("bm.testOf", { i: i + 1, n: tests.length }), " · ",
h("span", { class: "muted" }, test.id)),
h("div", { class: "muted small", style: "margin-top:6px; font-style:italic" }, "«" + test.prompt.slice(0, 110) + (test.prompt.length > 110 ? "…»" : "»")),
h("div", { class: "pbar", style: "margin-top:8px" },
h("div", { class: "pbar-fill det", style: `width:${Math.round((i / tests.length) * 100)}%` })))
);
@@ -152,16 +178,22 @@ export async function renderBenchmark() {
rec.tokS.push(compl / (gen / 1000));
}
if (info.ttft_ms != null) rec.ttft.push(info.ttft_ms);
rec.results.push({ id: test.id, cat: test.cat, ...ev, latency: Math.round(latency), answer: stripThink(text).slice(0, 300) });
const row = { id: test.id, cat: test.cat, ...ev, latency: Math.round(latency), cost: info.cost_usd || 0, answer: stripThink(text).slice(0, 300) };
if (mode === "routing") {
row.task = info.task_label || "—";
row.tier = info.tier || "—";
row.chosen = info.selected_model || "—";
row.source = info.route_source || "—";
row.expected = test.label; // null = classification not judged
row.taskOk = test.label ? test.label.includes(info.task_label) : null;
}
rec.results.push(row);
} catch (e) {
rec.results.push({ id: test.id, cat: test.cat, status: "fail", score: 0, note: String(e.message || e).slice(0, 80), latency: 0, answer: "" });
rec.failed = true;
}
renderResults(run, true); // live: строка появляется сразу после теста
}
const n = rec.results.length || 1;
rec.score = rec.results.reduce((a, r) => a + r.score, 0) / n;
rec.avgTokS = rec.tokS.length ? rec.tokS.reduce((a, b) => a + b, 0) / rec.tokS.length : null;
rec.avgTtft = rec.ttft.length ? rec.ttft.reduce((a, b) => a + b, 0) / rec.ttft.length : null;
if (stopFlag) break;
}
@@ -169,7 +201,18 @@ export async function renderBenchmark() {
running = false;
runBtn.disabled = false;
stopBtn.style.display = "none";
if (!stopFlag) pushHistory(run);
if (!stopFlag) {
pushHistory(run);
// финальный аккорд: короткий вердикт с процентами и деньгами
const first = run.models[Object.keys(run.models)[0]];
if (first) {
const st = stats(first);
const judged = first.results.filter((r) => r.taskOk != null);
const cls = judged.length ? ` · ${judged.filter((r) => r.taskOk).length}/${judged.length}` : "";
const total = Object.values(run.models).reduce((a, rec) => a + stats(rec).cost, 0);
toast(t("bm.verdict", { p: Math.round(st.score * 100) + "%" + cls, s: money(total) }), "ok", 6000);
}
}
renderResults(run);
renderHistory();
});
@@ -178,53 +221,123 @@ export async function renderBenchmark() {
return s === "pass" ? "✅" : s === "partial" ? "◐" : "❌";
}
function renderResults(run) {
function stats(rec) {
const n = rec.results.length || 1;
return {
score: rec.results.reduce((a, r) => a + r.score, 0) / n,
tokS: rec.tokS.length ? rec.tokS.reduce((a, b) => a + b, 0) / rec.tokS.length : null,
ttft: rec.ttft.length ? rec.ttft.reduce((a, b) => a + b, 0) / rec.ttft.length : null,
cost: rec.results.reduce((a, r) => a + (r.cost || 0), 0),
};
}
function renderResults(run, live) {
const models = Object.keys(run.models);
if (!models.length) {
mount(resultsHost);
return;
}
// summary bars, best score first
const sorted = models.slice().sort((a, b) => run.models[b].score - run.models[a].score);
const summary = h("div", {},
...sorted.map((m) => {
const r = run.models[m];
const pct = Math.round(r.score * 100);
return h("div", { class: "bm-sum" },
h("div", { class: "flex" },
h("b", { class: "mono grow" }, m),
h("span", { class: "badge " + (pct >= 80 ? "ok" : pct >= 50 ? "" : "bad") }, pct + "%"),
r.avgTokS != null ? h("span", { class: "muted small", style: "margin-left:8px" }, r.avgTokS.toFixed(1) + " tok/s") : null,
r.avgTtft != null ? h("span", { class: "muted small", style: "margin-left:8px" }, "TTFT " + ms(Math.round(r.avgTtft))) : null),
h("div", { class: "sysbar" }, h("i", { class: pct < 50 ? "bad" : "", style: `width:${pct}%` })));
}));
// detail table: rows = tests, one column per model
const header = h("tr", {}, h("th", {}, t("bm.test")), ...models.map((m) => h("th", { class: "mono" }, m)));
const rows = (run.models[models[0]].results || []).map((_, i) =>
h("tr", {},
h("td", {},
h("div", {}, run.models[models[0]].results[i].id),
h("div", { class: "muted small" }, run.models[models[0]].results[i].cat)),
...models.map((m) => {
const r = run.models[m].results[i];
if (!r) return h("td", {}, "—");
const cell = h("td", { class: "bm-cell", title: r.answer || r.note },
statusIcon(r.status) + " ",
h("span", { class: "muted small" }, r.note + (r.latency ? ` · ${(r.latency / 1000).toFixed(1)}s` : "")));
cell.addEventListener("click", () => {
mount(detail, h("div", { class: "card" },
h("div", { class: "card-title" }, `${r.id} · ${m} · ${statusIcon(r.status)}`),
h("pre", { class: "conv-log", style: "max-height:200px" }, r.answer || "—")));
});
return cell;
})));
const routing = run.mode === "routing";
const detail = h("div", {});
let summary;
if (routing) {
const rec = run.models[models[0]];
const st = stats(rec);
const judged = rec.results.filter((r) => r.taskOk != null);
const okCount = judged.filter((r) => r.taskOk).length;
// какие модели реально выбирал роутер
const dist = {};
for (const r of rec.results) {
if (!r.chosen) continue;
dist[r.chosen] = dist[r.chosen] || { n: 0, cost: 0 };
dist[r.chosen].n++;
dist[r.chosen].cost += r.cost || 0;
}
const pct = Math.round(st.score * 100);
summary = h("div", {},
h("div", { class: "kpis", style: "grid-template-columns: repeat(auto-fit, minmax(150px, 1fr))" },
h("div", { class: "kpi" }, h("div", { class: "big" }, pct + "%"), h("div", { class: "lbl" }, t("bm.answersOk"))),
h("div", { class: "kpi" }, h("div", { class: "big" }, judged.length ? `${okCount}/${judged.length}` : "—"), h("div", { class: "lbl" }, t("bm.classAcc"))),
h("div", { class: "kpi" }, h("div", { class: "big" }, st.ttft != null ? ms(Math.round(st.ttft)) : "—"), h("div", { class: "lbl" }, t("pg.ttft"))),
h("div", { class: "kpi" }, h("div", { class: "big" }, st.tokS != null ? st.tokS.toFixed(1) : "—"), h("div", { class: "lbl" }, "tok/s")),
h("div", { class: "kpi" }, h("div", { class: "big" }, money(st.cost)), h("div", { class: "lbl" }, t("bm.spent")))),
h("div", { class: "flex wrap", style: "gap:6px; margin-top:4px" },
h("span", { class: "muted small" }, t("bm.modelDist") + ":"),
...Object.entries(dist).map(([m, d]) =>
h("span", { class: "badge" }, `${m} × ${d.n}` + (d.cost > 0 ? ` · ${money(d.cost)}` : "")))));
} else {
const sorted = models.slice().sort((a, b) => stats(run.models[b]).score - stats(run.models[a]).score);
summary = h("div", {},
...sorted.map((m) => {
const st = stats(run.models[m]);
const pct = Math.round(st.score * 100);
return h("div", { class: "bm-sum" },
h("div", { class: "flex" },
h("b", { class: "mono grow" }, m),
h("span", { class: "badge " + (pct >= 80 ? "ok" : pct >= 50 ? "" : "bad") }, pct + "%"),
st.tokS != null ? h("span", { class: "muted small", style: "margin-left:8px" }, st.tokS.toFixed(1) + " tok/s") : null,
st.ttft != null ? h("span", { class: "muted small", style: "margin-left:8px" }, "TTFT " + ms(Math.round(st.ttft))) : null,
st.cost > 0 ? h("span", { class: "muted small", style: "margin-left:8px" }, t("bm.spent") + " " + money(st.cost)) : null),
h("div", { class: "sysbar" }, h("i", { class: pct < 50 ? "bad" : "", style: `width:${pct}%` })));
}));
}
function answerCell(r, m) {
const cell = h("td", { class: "bm-cell", title: r.answer || r.note },
statusIcon(r.status) + " ",
h("span", { class: "muted small" }, r.note + (r.latency ? ` · ${(r.latency / 1000).toFixed(1)}s` : "")));
cell.addEventListener("click", () => {
mount(detail, h("div", { class: "card" },
h("div", { class: "card-title" }, `${r.id} · ${m} · ${statusIcon(r.status)}`),
h("pre", { class: "conv-log", style: "max-height:200px" }, r.answer || "—")));
});
return cell;
}
let header, rows;
if (routing) {
const rec = run.models[models[0]];
header = h("tr", {},
h("th", {}, t("bm.test")),
h("th", {}, t("pg.task")),
h("th", {}, t("pg.tier")),
h("th", {}, t("pg.model")),
h("th", {}, t("bm.answer")));
rows = rec.results.map((r) =>
h("tr", {},
h("td", {}, h("div", {}, r.id), h("div", { class: "muted small" }, r.cat)),
h("td", {},
r.taskOk == null
? h("span", { class: "muted" }, r.task || "—")
: h("span", { class: r.taskOk ? "" : "err" },
(r.taskOk ? "✓ " : "✗ ") + r.task,
r.taskOk ? "" : h("div", { class: "muted small" }, t("bm.expectedLbl") + " " + (r.expected || []).join("/")))),
h("td", {}, r.tier ? h("span", { class: "badge tier-" + r.tier }, r.tier) : "—"),
h("td", {},
h("span", { class: "mono small" }, r.chosen || "—"),
r.cost > 0 ? h("div", { class: "muted small" }, money(r.cost)) : null,
r.source && r.source.includes("task-rule") ? h("div", { class: "badge", style: "margin-top:2px" }, "task-rule") : null),
answerCell(r, r.chosen || "cortiq-auto")));
} else {
header = h("tr", {}, h("th", {}, t("bm.test")), ...models.map((m) => h("th", { class: "mono" }, m)));
rows = (run.models[models[0]].results || []).map((_, i) =>
h("tr", {},
h("td", {},
h("div", {}, run.models[models[0]].results[i].id),
h("div", { class: "muted small" }, run.models[models[0]].results[i].cat)),
...models.map((m) => {
const r = run.models[m].results[i];
return r ? answerCell(r, m) : h("td", {}, "—");
})));
}
mount(resultsHost,
h("div", { class: "card" },
h("div", { class: "card-head" },
h("h3", {}, t("bm.results")),
h("span", { class: "card-head sub" }, new Date(run.ts).toLocaleString() + (run.quick ? " · " + t("bm.quick") : ""))),
h("h3", {}, (routing ? "🧭 " : "🎯 ") + t("bm.results")),
h("span", { class: "card-head sub" },
(live ? t("bm.liveRunning") + " · " : "") + new Date(run.ts).toLocaleString() + (run.quick ? " · " + t("bm.quick") : ""))),
summary,
h("div", { class: "table-wrap", style: "margin-top:14px" }, h("table", {}, h("thead", {}, header), h("tbody", {}, ...rows))),
h("div", { class: "muted small", style: "margin-top:6px" }, t("bm.cellHint"))),
@@ -241,12 +354,17 @@ export async function renderBenchmark() {
h("div", { class: "card-title" }, t("bm.history")),
...l.map((run) => {
const models = Object.keys(run.models);
const best = models.slice().sort((a, b) => run.models[b].score - run.models[a].score)[0];
const scoreOf = (m) => {
const rs = run.models[m].results || [];
return rs.length ? rs.reduce((a, r) => a + r.score, 0) / rs.length : 0;
};
const best = models.slice().sort((a, b) => scoreOf(b) - scoreOf(a))[0];
const row = h("div", { class: "flex bench-row", style: "cursor:pointer" },
h("span", {}, run.mode === "routing" ? "🧭" : "🎯"),
h("span", { class: "muted small" }, new Date(run.ts).toLocaleString()),
h("span", { class: "grow mono small" }, models.join(", ")),
h("span", { class: "grow mono small" }, run.mode === "routing" ? t("bm.mode.routing") : models.join(", ")),
run.quick ? h("span", { class: "badge" }, t("bm.quick")) : null,
best ? h("b", {}, Math.round(run.models[best].score * 100) + "%") : null);
best ? h("b", {}, Math.round(scoreOf(best) * 100) + "%") : null);
row.addEventListener("click", () => renderResults(run));
return row;
})));
@@ -288,9 +406,9 @@ export async function renderBenchmark() {
h("p", {}, t("bm.subtitle"))),
ids.length === 0 ? h("div", { class: "callout" }, t("routing.empty")) : null,
h("div", { class: "card" },
h("div", { class: "card-title" }, t("bm.models")),
h("div", { class: "flex wrap", style: "gap:10px" },
...modelCbs.map(({ id, cb }) => h("label", { class: "check" }, cb, h("span", { class: "mono" }, id)))),
modeSeg,
modeDesc,
modelsPick,
h("div", { class: "flex", style: "justify-content:space-between; margin-top:14px" },
h("label", { class: "check", style: "margin:0", title: t("bm.quickHint") }, quickCb, "⚡ " + t("bm.quickMode")),
h("div", { class: "flex", style: "gap:8px" }, stopBtn, runBtn)),