diff --git a/kipina-codebench/benchmark.mjs b/kipina-codebench/benchmark.mjs
index 30132c1..e7b8975 100644
--- a/kipina-codebench/benchmark.mjs
+++ b/kipina-codebench/benchmark.mjs
@@ -50,6 +50,12 @@ const FIX_SYSTEM = loadPrompt('fix');
// === Mallikohtaiset profiilit ===
const PROFILES = JSON.parse(readFileSync(join(__dirname, 'profiles.json'), 'utf-8'));
+function getGoldenForModel(model) {
+ const modelConf = PROFILES.models[model];
+ const goldenFile = modelConf?.golden || 'todo.md';
+ return goldenFile;
+}
+
function getCodePromptForModel(model) {
const modelConf = PROFILES.models[model];
const profile = modelConf?.profile || PROFILES.default_profile;
@@ -82,16 +88,16 @@ const LANG_CONFIG = {
};
const LCONF = LANG_CONFIG[LANG] || LANG_CONFIG.python;
-function loadGoldenExample() {
+function loadGoldenExample(model) {
// --compact: käytä tiivistettyä templaattia
if (COMPACT_MODE) {
const compactFile = LANG === 'rust' ? 'golden-compact-rs.md' : 'golden-compact-py.md';
const compactPath = join(__dirname, 'prompts', compactFile);
if (existsSync(compactPath)) return '\n' + readFileSync(compactPath, 'utf-8').trim() + '\n';
}
- // Markdown golden example (koodi + selitykset)
- const mdName = LANG === 'rust' ? 'todo-rs.md' : 'todo.md';
- const mdPath = join(GOLDEN_DIR, mdName);
+ // Mallikohtainen golden example profiilista
+ const goldenFile = model ? getGoldenForModel(model) : (LANG === 'rust' ? 'todo-rs.md' : 'todo.md');
+ const mdPath = join(GOLDEN_DIR, goldenFile);
if (existsSync(mdPath)) return '\n' + readFileSync(mdPath, 'utf-8').trim() + '\n';
// Fallback: erilliset tiedostot
const todoDir = join(GOLDEN_DIR, LCONF.goldenDir);
@@ -103,7 +109,6 @@ function loadGoldenExample() {
}
return example;
}
-const GOLDEN_EXAMPLE = loadGoldenExample();
// === Ajattelutagien siivous (gemma4, qwen3/3.5 ym.) ===
function stripThinking(text) {
@@ -322,7 +327,8 @@ async function runPipeline(model, scenario) {
// 3. LLM-koodigenerointi
console.log(` [3/5] Koodigenerointi (LLM)...`);
const fileCount = LCONF.required.length;
- const codePrompt = `${GOLDEN_EXAMPLE}\n---\n\nPROJECT REQUIREMENTS:\n${req.text}\n\nJSON SPECIFICATION:\n${JSON.stringify(spec, null, 2)}\n\nGenerate the complete project with all ${fileCount} files. Follow the reference implementation patterns exactly.`;
+ const goldenExample = loadGoldenExample(model);
+ const codePrompt = `${goldenExample}\n---\n\nPROJECT REQUIREMENTS:\n${req.text}\n\nJSON SPECIFICATION:\n${JSON.stringify(spec, null, 2)}\n\nGenerate the complete project with all ${fileCount} files. Follow the reference implementation patterns exactly.`;
result.promptChars = CODE_SYSTEM.length + codePrompt.length;
result.promptTokensEst = Math.round(result.promptChars / 4);
const codeTokens = LANG === 'rust' ? 12288 : 8192;
diff --git a/kipina-codebench/golden-examples/todo-readme.md b/kipina-codebench/golden-examples/todo-readme.md
new file mode 100644
index 0000000..5bf785e
--- /dev/null
+++ b/kipina-codebench/golden-examples/todo-readme.md
@@ -0,0 +1,217 @@
+# Todo App — FastAPI + SQLAlchemy + SQLite
+
+A simple todo CRUD API. Uses only the fields defined in the spec — no extra fields.
+
+## Project Structure
+
+```
+models.py # SQLAlchemy 2.0 models
+schemas.py # Pydantic v2 schemas
+main.py # FastAPI CRUD endpoints
+test_main.py # Pytest with TestClient
+```
+
+## models.py
+
+```python
+"""Tietokantamallit — SQLAlchemy 2.0, Mapped-tyypitys, SQLite."""
+
+from datetime import date
+
+from sqlalchemy import String, Text, Date, create_engine
+from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column, sessionmaker
+
+DATABASE_URL = "sqlite:///./app.db"
+engine = create_engine(DATABASE_URL, connect_args={"check_same_thread": False})
+SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+
+
+class Base(DeclarativeBase):
+ pass
+
+
+class Todo(Base):
+ """Tehtävä — otsikko, kuvaus, deadline, prioriteetti ja status."""
+
+ __tablename__ = "todos"
+
+ id: Mapped[int] = mapped_column(primary_key=True, index=True)
+ title: Mapped[str] = mapped_column(String(255))
+ description: Mapped[str | None] = mapped_column(Text, default=None)
+ due_date: Mapped[date | None] = mapped_column(Date, default=None)
+ priority: Mapped[int] = mapped_column(default=1)
+ status: Mapped[str] = mapped_column(String(20), default="pending")
+
+
+Base.metadata.create_all(bind=engine)
+```
+
+## schemas.py
+
+```python
+"""Pydantic v2 -skeemat — Create sisääntulolle, Response vastaukselle."""
+
+from datetime import date
+
+from pydantic import BaseModel, ConfigDict
+
+
+class TodoCreate(BaseModel):
+ """Uuden tehtävän luonti. Pakolliset: title."""
+
+ title: str
+ description: str | None = None
+ due_date: date | None = None
+ priority: int = 1
+ status: str = "pending"
+
+
+class TodoResponse(TodoCreate):
+ """Palautettava tehtävä — sisältää id:n."""
+
+ id: int
+ model_config = ConfigDict(from_attributes=True)
+```
+
+## main.py
+
+```python
+"""FastAPI CRUD — yksi endpoint-setti per entiteetti."""
+
+from fastapi import FastAPI, Depends, HTTPException
+from sqlalchemy.orm import Session
+
+from models import SessionLocal, Todo
+from schemas import TodoCreate, TodoResponse
+
+app = FastAPI()
+
+
+def get_db():
+ """Tietokantasessio per pyyntö."""
+ db = SessionLocal()
+ try:
+ yield db
+ finally:
+ db.close()
+
+
+@app.post("/todos/", response_model=TodoResponse, status_code=201)
+def create_todo(item: TodoCreate, db: Session = Depends(get_db)):
+ db_item = Todo(**item.model_dump())
+ db.add(db_item)
+ db.commit()
+ db.refresh(db_item)
+ return db_item
+
+
+@app.get("/todos/", response_model=list[TodoResponse])
+def list_todos(db: Session = Depends(get_db)):
+ return db.query(Todo).all()
+
+
+@app.get("/todos/{item_id}", response_model=TodoResponse)
+def get_todo(item_id: int, db: Session = Depends(get_db)):
+ item = db.query(Todo).filter(Todo.id == item_id).first()
+ if not item:
+ raise HTTPException(status_code=404, detail="Todo not found")
+ return item
+
+
+@app.put("/todos/{item_id}", response_model=TodoResponse)
+def update_todo(item_id: int, item: TodoCreate, db: Session = Depends(get_db)):
+ db_item = db.query(Todo).filter(Todo.id == item_id).first()
+ if not db_item:
+ raise HTTPException(status_code=404, detail="Todo not found")
+ for key, value in item.model_dump().items():
+ setattr(db_item, key, value)
+ db.commit()
+ db.refresh(db_item)
+ return db_item
+
+
+@app.delete("/todos/{item_id}", status_code=204)
+def delete_todo(item_id: int, db: Session = Depends(get_db)):
+ db_item = db.query(Todo).filter(Todo.id == item_id).first()
+ if not db_item:
+ raise HTTPException(status_code=404, detail="Todo not found")
+ db.delete(db_item)
+ db.commit()
+```
+
+## test_main.py
+
+Exactly 6 tests per entity. Database is shared — use `>= 1` not `== 1` in list tests.
+For child entities with foreign keys: create parent FIRST, then child with parent's id.
+
+```python
+"""Pytest — TestClient, erillinen test.db, uniikki data per testi."""
+
+from fastapi.testclient import TestClient
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+
+from main import app, get_db
+from models import Base
+
+test_engine = create_engine(
+ "sqlite:///./test.db", connect_args={"check_same_thread": False}
+)
+TestSession = sessionmaker(autocommit=False, autoflush=False, bind=test_engine)
+Base.metadata.create_all(bind=test_engine)
+
+
+def override_get_db():
+ db = TestSession()
+ try:
+ yield db
+ finally:
+ db.close()
+
+
+app.dependency_overrides[get_db] = override_get_db
+client = TestClient(app)
+
+
+def test_create_todo():
+ response = client.post("/todos/", json={"title": "Osta maitoa", "priority": 2})
+ assert response.status_code == 201
+ assert response.json()["title"] == "Osta maitoa"
+ assert "id" in response.json()
+
+
+def test_list_todos():
+ client.post("/todos/", json={"title": "Listattava tehtävä"})
+ response = client.get("/todos/")
+ assert response.status_code == 200
+ assert len(response.json()) >= 1
+
+
+def test_get_todo_by_id():
+ created = client.post("/todos/", json={"title": "Haettava tehtävä"}).json()
+ response = client.get(f"/todos/{created['id']}")
+ assert response.status_code == 200
+ assert response.json()["id"] == created["id"]
+
+
+def test_get_todo_not_found():
+ response = client.get("/todos/99999")
+ assert response.status_code == 404
+
+
+def test_update_todo():
+ created = client.post("/todos/", json={"title": "Vanha otsikko"}).json()
+ response = client.put(
+ f"/todos/{created['id']}", json={"title": "Uusi otsikko"}
+ )
+ assert response.status_code == 200
+ assert response.json()["title"] == "Uusi otsikko"
+
+
+def test_delete_todo():
+ created = client.post("/todos/", json={"title": "Poistettava"}).json()
+ response = client.delete(f"/todos/{created['id']}")
+ assert response.status_code == 204
+ response = client.get(f"/todos/{created['id']}")
+ assert response.status_code == 404
+```
diff --git a/kipina-codebench/profiles.json b/kipina-codebench/profiles.json
index d129276..167a429 100644
--- a/kipina-codebench/profiles.json
+++ b/kipina-codebench/profiles.json
@@ -12,9 +12,9 @@
"profile": "small",
"role": "primary",
"prompt": "code-small",
- "golden": "todo.md",
+ "golden": "todo-readme.md",
"vram": "8GB",
- "notes": "Kevyt pääkooderi. Todo/users 100p, blog heikko. Lyhyt prompti toimii paremmin."
+ "notes": "Kevyt pääkooderi. Todo/users 100p, blog heikko. README-muoto golden examplelle."
},
"codestral:22b": {
"profile": "large",
diff --git a/kipina-codebench/results/2026-04-14T10-59.html b/kipina-codebench/results/2026-04-14T10-59.html
new file mode 100644
index 0000000..4af497c
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T10-59.html
@@ -0,0 +1,183 @@
+
+
+
+
+
+Kipina Model Benchmark
+
+
+
+
+Kipina Model Benchmark
+
+
+
+
+Mallikohtainen yhteenveto
+
+
+Kaikki tulokset
+
+
+
+
+
diff --git a/kipina-codebench/results/2026-04-14T10-59.json b/kipina-codebench/results/2026-04-14T10-59.json
new file mode 100644
index 0000000..492c110
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T10-59.json
@@ -0,0 +1,69 @@
+[
+ {
+ "model": "qwen3:8b",
+ "scenario": "blog",
+ "reqOk": true,
+ "specOk": true,
+ "specEntities": 2,
+ "validationIssues": 0,
+ "fixRounds": 1,
+ "testsTotal": 11,
+ "testsPassed": 11,
+ "testsFailed": 0,
+ "totalDurationMs": 64124,
+ "totalTokens": 5689,
+ "avgTokPerSec": 98.61378134916481,
+ "promptChars": 12098,
+ "promptTokensEst": 3025,
+ "score": 90,
+ "stars": "★★★★★",
+ "error": null,
+ "profile": "small",
+ "promptName": "code-small",
+ "round": 1
+ },
+ {
+ "model": "qwen3:8b",
+ "scenario": "blog",
+ "reqOk": true,
+ "specOk": true,
+ "specEntities": 2,
+ "validationIssues": 0,
+ "fixRounds": 3,
+ "testsTotal": 0,
+ "testsPassed": 0,
+ "testsFailed": 0,
+ "totalDurationMs": 126014,
+ "totalTokens": 11162,
+ "avgTokPerSec": 97.09858655726343,
+ "promptChars": 12101,
+ "promptTokensEst": 3025,
+ "score": 0,
+ "stars": "☆☆☆☆☆",
+ "error": "Testit kaatuivat",
+ "profile": "small",
+ "promptName": "code-small",
+ "round": 2
+ },
+ {
+ "model": "qwen3:8b",
+ "scenario": "blog",
+ "reqOk": true,
+ "specOk": false,
+ "specEntities": 0,
+ "validationIssues": 0,
+ "fixRounds": 0,
+ "testsTotal": 0,
+ "testsPassed": 0,
+ "testsFailed": 0,
+ "totalDurationMs": 0,
+ "totalTokens": 0,
+ "avgTokPerSec": 0,
+ "promptChars": 0,
+ "promptTokensEst": 0,
+ "score": 0,
+ "stars": "",
+ "error": "JSON-speksi epäonnistui",
+ "round": 3
+ }
+]
\ No newline at end of file