CodeBench: combined-readme.md — todo + blog golden example 8b:lle
Molemmat esimerkit (single entity + FK relaatio) yhdessä tiedostossa. 1699 tokenia, 10.4% kontekstista. 8b näkee konkreettisen FK-patternen.
This commit is contained in:
204
kipina-codebench/golden-examples/combined-readme.md
Normal file
204
kipina-codebench/golden-examples/combined-readme.md
Normal file
@@ -0,0 +1,204 @@
|
|||||||
|
# Example 1: Todo App (single entity)
|
||||||
|
|
||||||
|
## 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):
|
||||||
|
__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
|
||||||
|
from datetime import date
|
||||||
|
from pydantic import BaseModel, ConfigDict
|
||||||
|
|
||||||
|
class TodoCreate(BaseModel):
|
||||||
|
title: str
|
||||||
|
description: str | None = None
|
||||||
|
due_date: date | None = None
|
||||||
|
priority: int = 1
|
||||||
|
status: str = "pending"
|
||||||
|
|
||||||
|
class TodoResponse(TodoCreate):
|
||||||
|
id: int
|
||||||
|
model_config = ConfigDict(from_attributes=True)
|
||||||
|
```
|
||||||
|
|
||||||
|
## test_main.py — exactly 6 tests per entity
|
||||||
|
|
||||||
|
```python
|
||||||
|
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 "id" in response.json()
|
||||||
|
|
||||||
|
def test_list_todos():
|
||||||
|
client.post("/todos/", json={"title": "Listattava"})
|
||||||
|
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"}).json()
|
||||||
|
response = client.get(f"/todos/{created['id']}")
|
||||||
|
assert response.status_code == 200
|
||||||
|
|
||||||
|
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"}).json()
|
||||||
|
response = client.put(f"/todos/{created['id']}", json={"title": "Uusi"})
|
||||||
|
assert response.status_code == 200
|
||||||
|
|
||||||
|
def test_delete_todo():
|
||||||
|
created = client.post("/todos/", json={"title": "Poistettava"}).json()
|
||||||
|
response = client.delete(f"/todos/{created['id']}")
|
||||||
|
assert response.status_code == 204
|
||||||
|
```
|
||||||
|
|
||||||
|
# Example 2: Blog (two entities with ForeignKey)
|
||||||
|
|
||||||
|
NOTE: ForeignKey is imported from sqlalchemy, NOT from sqlalchemy.orm!
|
||||||
|
|
||||||
|
## models.py
|
||||||
|
|
||||||
|
```python
|
||||||
|
from datetime import datetime
|
||||||
|
from sqlalchemy import String, Text, DateTime, ForeignKey, create_engine
|
||||||
|
from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column, relationship, 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 Author(Base):
|
||||||
|
__tablename__ = "authors"
|
||||||
|
id: Mapped[int] = mapped_column(primary_key=True, index=True)
|
||||||
|
name: Mapped[str] = mapped_column(String(255))
|
||||||
|
email: Mapped[str] = mapped_column(String(255), unique=True)
|
||||||
|
bio: Mapped[str | None] = mapped_column(Text, default=None)
|
||||||
|
posts: Mapped[list["Post"]] = relationship(back_populates="author")
|
||||||
|
|
||||||
|
class Post(Base):
|
||||||
|
__tablename__ = "posts"
|
||||||
|
id: Mapped[int] = mapped_column(primary_key=True, index=True)
|
||||||
|
title: Mapped[str] = mapped_column(String(255))
|
||||||
|
content: Mapped[str] = mapped_column(Text)
|
||||||
|
author_id: Mapped[int] = mapped_column(ForeignKey("authors.id"))
|
||||||
|
published_at: Mapped[datetime | None] = mapped_column(DateTime, default=None)
|
||||||
|
status: Mapped[str] = mapped_column(String(20), default="draft")
|
||||||
|
author: Mapped["Author"] = relationship(back_populates="posts")
|
||||||
|
|
||||||
|
Base.metadata.create_all(bind=engine)
|
||||||
|
```
|
||||||
|
|
||||||
|
## schemas.py
|
||||||
|
|
||||||
|
```python
|
||||||
|
from datetime import datetime
|
||||||
|
from pydantic import BaseModel, ConfigDict
|
||||||
|
|
||||||
|
class AuthorCreate(BaseModel):
|
||||||
|
name: str
|
||||||
|
email: str
|
||||||
|
bio: str | None = None
|
||||||
|
|
||||||
|
class AuthorResponse(AuthorCreate):
|
||||||
|
id: int
|
||||||
|
model_config = ConfigDict(from_attributes=True)
|
||||||
|
|
||||||
|
class PostCreate(BaseModel):
|
||||||
|
title: str
|
||||||
|
content: str
|
||||||
|
author_id: int
|
||||||
|
published_at: datetime | None = None
|
||||||
|
status: str = "draft"
|
||||||
|
|
||||||
|
class PostResponse(PostCreate):
|
||||||
|
id: int
|
||||||
|
model_config = ConfigDict(from_attributes=True)
|
||||||
|
```
|
||||||
|
|
||||||
|
## test_main.py — 6 tests per entity, create parent FIRST for child tests
|
||||||
|
|
||||||
|
```python
|
||||||
|
client = TestClient(app) # same setup as above
|
||||||
|
|
||||||
|
def _create_author(name="Kirjailija", email=None):
|
||||||
|
if email is None:
|
||||||
|
email = f"{name.lower().replace(' ', '.')}@example.com"
|
||||||
|
return client.post("/authors/", json={"name": name, "email": email}).json()
|
||||||
|
|
||||||
|
def test_create_author():
|
||||||
|
response = client.post("/authors/", json={"name": "Aleksis Kivi", "email": "aleksis@example.com"})
|
||||||
|
assert response.status_code == 201
|
||||||
|
|
||||||
|
def test_list_authors():
|
||||||
|
_create_author("Minna Canth", "minna@example.com")
|
||||||
|
response = client.get("/authors/")
|
||||||
|
assert response.status_code == 200
|
||||||
|
assert len(response.json()) >= 1
|
||||||
|
|
||||||
|
# ... (same pattern: get_by_id, not_found, update, delete)
|
||||||
|
|
||||||
|
def test_create_post():
|
||||||
|
author = _create_author("Tove Jansson", "tove@example.com")
|
||||||
|
response = client.post("/posts/", json={"title": "Artikkeli", "content": "Sisältö", "author_id": author["id"]})
|
||||||
|
assert response.status_code == 201
|
||||||
|
|
||||||
|
def test_update_post():
|
||||||
|
author = _create_author("Joel Lehtonen", "joel@example.com")
|
||||||
|
created = client.post("/posts/", json={"title": "Vanha", "content": "Teksti", "author_id": author["id"]}).json()
|
||||||
|
response = client.put(f"/posts/{created['id']}", json={"title": "Uusi", "content": "Muokattu", "author_id": author["id"]})
|
||||||
|
assert response.status_code == 200
|
||||||
|
|
||||||
|
def test_delete_post():
|
||||||
|
author = _create_author("Aino Kallas", "aino@example.com")
|
||||||
|
created = client.post("/posts/", json={"title": "Poistettava", "content": "Poistetaan", "author_id": author["id"]}).json()
|
||||||
|
response = client.delete(f"/posts/{created['id']}")
|
||||||
|
assert response.status_code == 204
|
||||||
|
```
|
||||||
@@ -12,7 +12,7 @@
|
|||||||
"profile": "small",
|
"profile": "small",
|
||||||
"role": "primary",
|
"role": "primary",
|
||||||
"prompt": "code-small",
|
"prompt": "code-small",
|
||||||
"golden": "todo-readme.md",
|
"golden": "combined-readme.md",
|
||||||
"vram": "8GB",
|
"vram": "8GB",
|
||||||
"notes": "Kevyt pääkooderi. Todo/users 100p, blog heikko. README-muoto golden examplelle."
|
"notes": "Kevyt pääkooderi. Todo/users 100p, blog heikko. README-muoto golden examplelle."
|
||||||
},
|
},
|
||||||
|
|||||||
183
kipina-codebench/results/2026-04-14T11-06.html
Normal file
183
kipina-codebench/results/2026-04-14T11-06.html
Normal file
@@ -0,0 +1,183 @@
|
|||||||
|
<!DOCTYPE html>
|
||||||
|
<html lang="fi">
|
||||||
|
<head>
|
||||||
|
<meta charset="UTF-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||||
|
<title>Kipina Model Benchmark</title>
|
||||||
|
<style>
|
||||||
|
:root { --bg: #0d1117; --card: #161b22; --border: #30363d; --text: #e6edf3; --dim: #8b949e; --green: #3fb950; --yellow: #d29922; --red: #f85149; --blue: #58a6ff; }
|
||||||
|
* { box-sizing: border-box; margin: 0; padding: 0; }
|
||||||
|
body { font-family: -apple-system, 'Segoe UI', Helvetica, Arial, sans-serif; background: var(--bg); color: var(--text); padding: 2rem; max-width: 1400px; margin: 0 auto; }
|
||||||
|
h1 { font-size: 1.5rem; margin-bottom: 0.5rem; }
|
||||||
|
.meta { color: var(--dim); font-size: 0.85rem; margin-bottom: 2rem; }
|
||||||
|
.cards { display: grid; grid-template-columns: repeat(auto-fit, minmax(180px, 1fr)); gap: 1rem; margin-bottom: 2rem; }
|
||||||
|
.card { background: var(--card); border: 1px solid var(--border); border-radius: 8px; padding: 1rem; }
|
||||||
|
.card .label { color: var(--dim); font-size: 0.75rem; text-transform: uppercase; letter-spacing: 0.05em; }
|
||||||
|
.card .value { font-size: 1.8rem; font-weight: 600; margin-top: 0.25rem; }
|
||||||
|
.card .sub { color: var(--dim); font-size: 0.8rem; margin-top: 0.25rem; }
|
||||||
|
table { width: 100%; border-collapse: collapse; background: var(--card); border: 1px solid var(--border); border-radius: 8px; overflow: hidden; margin-bottom: 2rem; }
|
||||||
|
th { background: #1c2128; text-align: left; padding: 0.6rem 0.8rem; font-size: 0.75rem; text-transform: uppercase; letter-spacing: 0.05em; color: var(--dim); cursor: pointer; user-select: none; white-space: nowrap; }
|
||||||
|
th:hover { color: var(--text); }
|
||||||
|
th.sorted-asc::after { content: ' ▲'; }
|
||||||
|
th.sorted-desc::after { content: ' ▼'; }
|
||||||
|
td { padding: 0.5rem 0.8rem; border-top: 1px solid var(--border); font-size: 0.85rem; white-space: nowrap; }
|
||||||
|
tr:hover td { background: #1c2128; }
|
||||||
|
.pass { color: var(--green); }
|
||||||
|
.partial { color: var(--yellow); }
|
||||||
|
.fail { color: var(--red); }
|
||||||
|
.stars { letter-spacing: 1px; }
|
||||||
|
.bar { display: inline-block; height: 8px; border-radius: 4px; vertical-align: middle; }
|
||||||
|
.bar-bg { background: var(--border); }
|
||||||
|
.bar-fill { background: var(--green); }
|
||||||
|
.bar-partial { background: var(--yellow); }
|
||||||
|
.model-name { font-weight: 600; }
|
||||||
|
h2 { font-size: 1.1rem; margin-bottom: 1rem; color: var(--dim); }
|
||||||
|
.summary-table th:first-child, .summary-table td:first-child { min-width: 200px; }
|
||||||
|
</style>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
|
||||||
|
<h1>Kipina Model Benchmark</h1>
|
||||||
|
<div class="meta" id="meta"></div>
|
||||||
|
|
||||||
|
<div class="cards" id="cards"></div>
|
||||||
|
|
||||||
|
<h2>Mallikohtainen yhteenveto</h2>
|
||||||
|
<table class="summary-table" id="summary-table"><thead></thead><tbody></tbody></table>
|
||||||
|
|
||||||
|
<h2>Kaikki tulokset</h2>
|
||||||
|
<table id="results-table"><thead></thead><tbody></tbody></table>
|
||||||
|
|
||||||
|
<script>
|
||||||
|
const RAW = [{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":3,"testsTotal":12,"testsPassed":10,"testsFailed":2,"totalDurationMs":139308,"totalTokens":11782,"avgTokPerSec":96.85039238572556,"promptChars":11148,"promptTokensEst":2787,"score":70,"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":1,"testsPassed":0,"testsFailed":1,"totalDurationMs":132306,"totalTokens":11671,"avgTokPerSec":96.88921767777383,"promptChars":11267,"promptTokensEst":2817,"score":20,"stars":"★☆☆☆☆","error":"Syntaksivirhe","profile":"small","promptName":"code-small","round":2},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":3,"testsTotal":12,"testsPassed":11,"testsFailed":1,"totalDurationMs":126092,"totalTokens":11132,"avgTokPerSec":96.98598556369416,"promptChars":11292,"promptTokensEst":2823,"score":75,"stars":"★★★★☆","error":null,"profile":"small","promptName":"code-small","round":3}];
|
||||||
|
|
||||||
|
const starsFor = s => s >= 90 ? '★★★★★' : s >= 70 ? '★★★★☆' : s >= 50 ? '★★★☆☆' : s >= 25 ? '★★☆☆☆' : s > 0 ? '★☆☆☆☆' : '☆☆☆☆☆';
|
||||||
|
function calcScore(r) {
|
||||||
|
if (r.error && r.testsTotal === 0) return 0;
|
||||||
|
let s = 0;
|
||||||
|
if (r.specOk) s += 10;
|
||||||
|
if (!r.error || r.testsTotal > 0) s += 10;
|
||||||
|
if (r.testsTotal > 0) s += Math.round((r.testsPassed / r.testsTotal) * 60);
|
||||||
|
s += Math.max(0, 20 - (r.fixRounds || 0) * 10);
|
||||||
|
return Math.min(100, s);
|
||||||
|
}
|
||||||
|
// Laske pisteet jos puuttuvat
|
||||||
|
const DATA = RAW.map(r => {
|
||||||
|
if (r.score == null) r.score = calcScore(r);
|
||||||
|
if (!r.stars) r.stars = starsFor(r.score);
|
||||||
|
if (!r.promptTokensEst) r.promptTokensEst = r.promptChars ? Math.round(r.promptChars / 4) : 0;
|
||||||
|
return r;
|
||||||
|
});
|
||||||
|
const cls = r => (!r.error && r.testsPassed === r.testsTotal && r.testsTotal > 0) ? 'pass' : (r.testsTotal > 0 && r.testsPassed > 0) ? 'partial' : 'fail';
|
||||||
|
const pctBar = (passed, total, w=80) => {
|
||||||
|
if (total === 0) return '-';
|
||||||
|
const pct = passed/total*100;
|
||||||
|
const c = pct === 100 ? 'bar-fill' : 'bar-partial';
|
||||||
|
return `<span class="bar bar-bg" style="width:${w}px"><span class="bar ${c}" style="width:${Math.round(pct/100*w)}px"></span></span> ${passed}/${total}`;
|
||||||
|
};
|
||||||
|
|
||||||
|
// Meta
|
||||||
|
const totalTime = DATA.reduce((s,r) => s + r.totalDurationMs, 0);
|
||||||
|
document.getElementById('meta').textContent = `${new Date().toLocaleDateString('fi-FI')} — ${DATA.length} ajoa — ${(totalTime/1000/60).toFixed(1)} min`;
|
||||||
|
|
||||||
|
// Cards
|
||||||
|
const models = [...new Set(DATA.map(r => r.model))];
|
||||||
|
const scenarios = [...new Set(DATA.map(r => r.scenario))];
|
||||||
|
const avgScore = DATA.length ? Math.round(DATA.reduce((s,r) => s + r.score, 0) / DATA.length) : 0;
|
||||||
|
const totalPassed = DATA.reduce((s,r) => s + r.testsPassed, 0);
|
||||||
|
const totalTests = DATA.reduce((s,r) => s + r.testsTotal, 0);
|
||||||
|
const passRate = totalTests ? Math.round(totalPassed/totalTests*100) : 0;
|
||||||
|
const bestModel = models.map(m => {
|
||||||
|
const mrs = DATA.filter(r => r.model === m);
|
||||||
|
return { model: m, avg: Math.round(mrs.reduce((s,r) => s + r.score, 0) / mrs.length) };
|
||||||
|
}).sort((a,b) => b.avg - a.avg)[0];
|
||||||
|
const fastestModel = models.map(m => {
|
||||||
|
const mrs = DATA.filter(r => r.model === m);
|
||||||
|
return { model: m, speed: Math.round(mrs.reduce((s,r) => s + r.avgTokPerSec, 0) / mrs.length) };
|
||||||
|
}).sort((a,b) => b.speed - a.speed)[0];
|
||||||
|
|
||||||
|
document.getElementById('cards').innerHTML = `
|
||||||
|
<div class="card"><div class="label">Keskiarvo</div><div class="value">${starsFor(avgScore)}</div><div class="sub">${avgScore} pistetta</div></div>
|
||||||
|
<div class="card"><div class="label">Testien läpäisy</div><div class="value">${passRate}%</div><div class="sub">${totalPassed}/${totalTests} testiä</div></div>
|
||||||
|
<div class="card"><div class="label">Paras malli</div><div class="value" style="font-size:1.2rem">${bestModel?.model || '-'}</div><div class="sub">${bestModel?.avg || 0}p</div></div>
|
||||||
|
<div class="card"><div class="label">Nopein</div><div class="value" style="font-size:1.2rem">${fastestModel?.model || '-'}</div><div class="sub">${fastestModel?.speed || 0} tok/s</div></div>
|
||||||
|
<div class="card"><div class="label">Malleja</div><div class="value">${models.length}</div><div class="sub">${scenarios.length} skenaariota</div></div>
|
||||||
|
<div class="card"><div class="label">Kokonaisaika</div><div class="value">${(totalTime/1000/60).toFixed(1)}</div><div class="sub">minuuttia</div></div>
|
||||||
|
`;
|
||||||
|
|
||||||
|
// Summary table
|
||||||
|
const sumHead = document.querySelector('#summary-table thead');
|
||||||
|
const sumBody = document.querySelector('#summary-table tbody');
|
||||||
|
sumHead.innerHTML = '<tr><th>Malli</th>' + scenarios.map(s => `<th>${s}</th>`).join('') + '<th>Yht.</th><th>Out tok</th><th>Aika</th><th>tok/s</th><th>Pisteet</th></tr>';
|
||||||
|
|
||||||
|
const modelRows = models.map(m => {
|
||||||
|
const mrs = DATA.filter(r => r.model === m);
|
||||||
|
const tp = mrs.reduce((s,r) => s + r.testsPassed, 0);
|
||||||
|
const tt = mrs.reduce((s,r) => s + r.testsTotal, 0);
|
||||||
|
const tok = mrs.reduce((s,r) => s + r.totalTokens, 0);
|
||||||
|
const time = mrs.reduce((s,r) => s + r.totalDurationMs, 0);
|
||||||
|
const speed = Math.round(mrs.reduce((s,r) => s + r.avgTokPerSec, 0) / mrs.length);
|
||||||
|
const avg = Math.round(mrs.reduce((s,r) => s + r.score, 0) / mrs.length);
|
||||||
|
const scenCols = scenarios.map(s => {
|
||||||
|
const r = mrs.find(r => r.scenario === s);
|
||||||
|
if (!r) return '<td>-</td>';
|
||||||
|
return `<td class="${cls(r)}">${pctBar(r.testsPassed, r.testsTotal, 60)} <span style="color:var(--dim)">${(r.totalDurationMs/1000).toFixed(0)}s</span></td>`;
|
||||||
|
}).join('');
|
||||||
|
return { avg, html: `<tr><td class="model-name">${m}</td>${scenCols}<td>${pctBar(tp, tt)}</td><td>${(tok/1000).toFixed(1)}K</td><td>${(time/1000).toFixed(0)}s</td><td>${speed}</td><td><span class="stars">${starsFor(avg)}</span> ${avg}p</td></tr>` };
|
||||||
|
}).sort((a,b) => b.avg - a.avg);
|
||||||
|
sumBody.innerHTML = modelRows.map(r => r.html).join('');
|
||||||
|
|
||||||
|
// Results table
|
||||||
|
const resHead = document.querySelector('#results-table thead');
|
||||||
|
const resBody = document.querySelector('#results-table tbody');
|
||||||
|
const resCols = ['Malli','Skenaario','Speksi','Testit','Korjaus','Ctx','Out tok','Aika','tok/s','Pisteet'];
|
||||||
|
resHead.innerHTML = '<tr>' + resCols.map((c,i) => `<th data-col="${i}">${c}</th>`).join('') + '</tr>';
|
||||||
|
|
||||||
|
let sortCol = 9, sortAsc = false;
|
||||||
|
function renderResults() {
|
||||||
|
const sorted = [...DATA].sort((a,b) => {
|
||||||
|
const vals = [
|
||||||
|
[a.model, b.model],
|
||||||
|
[a.scenario, b.scenario],
|
||||||
|
[a.specEntities, b.specEntities],
|
||||||
|
[a.testsPassed/Math.max(a.testsTotal,1), b.testsPassed/Math.max(b.testsTotal,1)],
|
||||||
|
[a.fixRounds, b.fixRounds],
|
||||||
|
[a.promptTokensEst, b.promptTokensEst],
|
||||||
|
[a.totalTokens, b.totalTokens],
|
||||||
|
[a.totalDurationMs, b.totalDurationMs],
|
||||||
|
[a.avgTokPerSec, b.avgTokPerSec],
|
||||||
|
[a.score, b.score],
|
||||||
|
][sortCol];
|
||||||
|
const cmp = typeof vals[0] === 'string' ? vals[0].localeCompare(vals[1]) : vals[0] - vals[1];
|
||||||
|
return sortAsc ? cmp : -cmp;
|
||||||
|
});
|
||||||
|
resBody.innerHTML = sorted.map(r => {
|
||||||
|
const c = cls(r);
|
||||||
|
return `<tr>
|
||||||
|
<td class="model-name">${r.model}</td>
|
||||||
|
<td>${r.scenario}</td>
|
||||||
|
<td>${r.specOk ? `✓ ${r.specEntities}e` : '<span class="fail">✗</span>'}</td>
|
||||||
|
<td class="${c}">${pctBar(r.testsPassed, r.testsTotal)}</td>
|
||||||
|
<td>${r.fixRounds > 0 ? r.fixRounds + '×' : '-'}</td>
|
||||||
|
<td>${r.promptTokensEst > 0 ? '~'+(r.promptTokensEst/1000).toFixed(1)+'K' : '-'}</td>
|
||||||
|
<td>${r.totalTokens > 0 ? (r.totalTokens/1000).toFixed(1)+'K' : '-'}</td>
|
||||||
|
<td>${(r.totalDurationMs/1000).toFixed(0)}s</td>
|
||||||
|
<td>${r.avgTokPerSec.toFixed(0)}</td>
|
||||||
|
<td><span class="stars">${r.stars}</span> ${r.score}p</td>
|
||||||
|
</tr>`;
|
||||||
|
}).join('');
|
||||||
|
document.querySelectorAll('#results-table th').forEach((th,i) => {
|
||||||
|
th.className = i === sortCol ? (sortAsc ? 'sorted-asc' : 'sorted-desc') : '';
|
||||||
|
});
|
||||||
|
}
|
||||||
|
document.querySelector('#results-table thead').addEventListener('click', e => {
|
||||||
|
const col = parseInt(e.target.dataset.col);
|
||||||
|
if (isNaN(col)) return;
|
||||||
|
if (sortCol === col) sortAsc = !sortAsc;
|
||||||
|
else { sortCol = col; sortAsc = false; }
|
||||||
|
renderResults();
|
||||||
|
});
|
||||||
|
renderResults();
|
||||||
|
</script>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
71
kipina-codebench/results/2026-04-14T11-06.json
Normal file
71
kipina-codebench/results/2026-04-14T11-06.json
Normal file
@@ -0,0 +1,71 @@
|
|||||||
|
[
|
||||||
|
{
|
||||||
|
"model": "qwen3:8b",
|
||||||
|
"scenario": "blog",
|
||||||
|
"reqOk": true,
|
||||||
|
"specOk": true,
|
||||||
|
"specEntities": 2,
|
||||||
|
"validationIssues": 0,
|
||||||
|
"fixRounds": 3,
|
||||||
|
"testsTotal": 12,
|
||||||
|
"testsPassed": 10,
|
||||||
|
"testsFailed": 2,
|
||||||
|
"totalDurationMs": 139308,
|
||||||
|
"totalTokens": 11782,
|
||||||
|
"avgTokPerSec": 96.85039238572556,
|
||||||
|
"promptChars": 11148,
|
||||||
|
"promptTokensEst": 2787,
|
||||||
|
"score": 70,
|
||||||
|
"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": 1,
|
||||||
|
"testsPassed": 0,
|
||||||
|
"testsFailed": 1,
|
||||||
|
"totalDurationMs": 132306,
|
||||||
|
"totalTokens": 11671,
|
||||||
|
"avgTokPerSec": 96.88921767777383,
|
||||||
|
"promptChars": 11267,
|
||||||
|
"promptTokensEst": 2817,
|
||||||
|
"score": 20,
|
||||||
|
"stars": "★☆☆☆☆",
|
||||||
|
"error": "Syntaksivirhe",
|
||||||
|
"profile": "small",
|
||||||
|
"promptName": "code-small",
|
||||||
|
"round": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"model": "qwen3:8b",
|
||||||
|
"scenario": "blog",
|
||||||
|
"reqOk": true,
|
||||||
|
"specOk": true,
|
||||||
|
"specEntities": 2,
|
||||||
|
"validationIssues": 0,
|
||||||
|
"fixRounds": 3,
|
||||||
|
"testsTotal": 12,
|
||||||
|
"testsPassed": 11,
|
||||||
|
"testsFailed": 1,
|
||||||
|
"totalDurationMs": 126092,
|
||||||
|
"totalTokens": 11132,
|
||||||
|
"avgTokPerSec": 96.98598556369416,
|
||||||
|
"promptChars": 11292,
|
||||||
|
"promptTokensEst": 2823,
|
||||||
|
"score": 75,
|
||||||
|
"stars": "★★★★☆",
|
||||||
|
"error": null,
|
||||||
|
"profile": "small",
|
||||||
|
"promptName": "code-small",
|
||||||
|
"round": 3
|
||||||
|
}
|
||||||
|
]
|
||||||
183
kipina-codebench/results/2026-04-14T11-15.html
Normal file
183
kipina-codebench/results/2026-04-14T11-15.html
Normal file
@@ -0,0 +1,183 @@
|
|||||||
|
<!DOCTYPE html>
|
||||||
|
<html lang="fi">
|
||||||
|
<head>
|
||||||
|
<meta charset="UTF-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||||
|
<title>Kipina Model Benchmark</title>
|
||||||
|
<style>
|
||||||
|
:root { --bg: #0d1117; --card: #161b22; --border: #30363d; --text: #e6edf3; --dim: #8b949e; --green: #3fb950; --yellow: #d29922; --red: #f85149; --blue: #58a6ff; }
|
||||||
|
* { box-sizing: border-box; margin: 0; padding: 0; }
|
||||||
|
body { font-family: -apple-system, 'Segoe UI', Helvetica, Arial, sans-serif; background: var(--bg); color: var(--text); padding: 2rem; max-width: 1400px; margin: 0 auto; }
|
||||||
|
h1 { font-size: 1.5rem; margin-bottom: 0.5rem; }
|
||||||
|
.meta { color: var(--dim); font-size: 0.85rem; margin-bottom: 2rem; }
|
||||||
|
.cards { display: grid; grid-template-columns: repeat(auto-fit, minmax(180px, 1fr)); gap: 1rem; margin-bottom: 2rem; }
|
||||||
|
.card { background: var(--card); border: 1px solid var(--border); border-radius: 8px; padding: 1rem; }
|
||||||
|
.card .label { color: var(--dim); font-size: 0.75rem; text-transform: uppercase; letter-spacing: 0.05em; }
|
||||||
|
.card .value { font-size: 1.8rem; font-weight: 600; margin-top: 0.25rem; }
|
||||||
|
.card .sub { color: var(--dim); font-size: 0.8rem; margin-top: 0.25rem; }
|
||||||
|
table { width: 100%; border-collapse: collapse; background: var(--card); border: 1px solid var(--border); border-radius: 8px; overflow: hidden; margin-bottom: 2rem; }
|
||||||
|
th { background: #1c2128; text-align: left; padding: 0.6rem 0.8rem; font-size: 0.75rem; text-transform: uppercase; letter-spacing: 0.05em; color: var(--dim); cursor: pointer; user-select: none; white-space: nowrap; }
|
||||||
|
th:hover { color: var(--text); }
|
||||||
|
th.sorted-asc::after { content: ' ▲'; }
|
||||||
|
th.sorted-desc::after { content: ' ▼'; }
|
||||||
|
td { padding: 0.5rem 0.8rem; border-top: 1px solid var(--border); font-size: 0.85rem; white-space: nowrap; }
|
||||||
|
tr:hover td { background: #1c2128; }
|
||||||
|
.pass { color: var(--green); }
|
||||||
|
.partial { color: var(--yellow); }
|
||||||
|
.fail { color: var(--red); }
|
||||||
|
.stars { letter-spacing: 1px; }
|
||||||
|
.bar { display: inline-block; height: 8px; border-radius: 4px; vertical-align: middle; }
|
||||||
|
.bar-bg { background: var(--border); }
|
||||||
|
.bar-fill { background: var(--green); }
|
||||||
|
.bar-partial { background: var(--yellow); }
|
||||||
|
.model-name { font-weight: 600; }
|
||||||
|
h2 { font-size: 1.1rem; margin-bottom: 1rem; color: var(--dim); }
|
||||||
|
.summary-table th:first-child, .summary-table td:first-child { min-width: 200px; }
|
||||||
|
</style>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
|
||||||
|
<h1>Kipina Model Benchmark</h1>
|
||||||
|
<div class="meta" id="meta"></div>
|
||||||
|
|
||||||
|
<div class="cards" id="cards"></div>
|
||||||
|
|
||||||
|
<h2>Mallikohtainen yhteenveto</h2>
|
||||||
|
<table class="summary-table" id="summary-table"><thead></thead><tbody></tbody></table>
|
||||||
|
|
||||||
|
<h2>Kaikki tulokset</h2>
|
||||||
|
<table id="results-table"><thead></thead><tbody></tbody></table>
|
||||||
|
|
||||||
|
<script>
|
||||||
|
const RAW = [{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":1,"validationIssues":0,"fixRounds":3,"testsTotal":11,"testsPassed":9,"testsFailed":2,"totalDurationMs":75178,"totalTokens":9916,"avgTokPerSec":142.94675043471062,"promptChars":10516,"promptTokensEst":2629,"score":69,"stars":"★★★☆☆","error":null,"profile":"small","promptName":"code-small","round":1},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":1,"fixRounds":5,"testsTotal":0,"testsPassed":0,"testsFailed":0,"totalDurationMs":98787,"totalTokens":12904,"avgTokPerSec":141.16873850064812,"promptChars":11810,"promptTokensEst":2953,"score":0,"stars":"☆☆☆☆☆","error":"Testit kaatuivat","profile":"small","promptName":"code-small","round":2},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":3,"testsTotal":1,"testsPassed":0,"testsFailed":1,"totalDurationMs":81763,"totalTokens":10277,"avgTokPerSec":134.82946940948588,"promptChars":11534,"promptTokensEst":2884,"score":20,"stars":"★☆☆☆☆","error":"Syntaksivirhe","profile":"small","promptName":"code-small","round":3},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":1,"validationIssues":0,"fixRounds":3,"testsTotal":1,"testsPassed":0,"testsFailed":1,"totalDurationMs":88517,"totalTokens":11280,"avgTokPerSec":136.63597159351744,"promptChars":10568,"promptTokensEst":2642,"score":20,"stars":"★☆☆☆☆","error":"Syntaksivirhe","profile":"small","promptName":"code-small","round":4},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":3,"testsTotal":12,"testsPassed":9,"testsFailed":3,"totalDurationMs":87817,"totalTokens":11171,"avgTokPerSec":136.1538785139482,"promptChars":11627,"promptTokensEst":2907,"score":65,"stars":"★★★☆☆","error":null,"profile":"small","promptName":"code-small","round":5}];
|
||||||
|
|
||||||
|
const starsFor = s => s >= 90 ? '★★★★★' : s >= 70 ? '★★★★☆' : s >= 50 ? '★★★☆☆' : s >= 25 ? '★★☆☆☆' : s > 0 ? '★☆☆☆☆' : '☆☆☆☆☆';
|
||||||
|
function calcScore(r) {
|
||||||
|
if (r.error && r.testsTotal === 0) return 0;
|
||||||
|
let s = 0;
|
||||||
|
if (r.specOk) s += 10;
|
||||||
|
if (!r.error || r.testsTotal > 0) s += 10;
|
||||||
|
if (r.testsTotal > 0) s += Math.round((r.testsPassed / r.testsTotal) * 60);
|
||||||
|
s += Math.max(0, 20 - (r.fixRounds || 0) * 10);
|
||||||
|
return Math.min(100, s);
|
||||||
|
}
|
||||||
|
// Laske pisteet jos puuttuvat
|
||||||
|
const DATA = RAW.map(r => {
|
||||||
|
if (r.score == null) r.score = calcScore(r);
|
||||||
|
if (!r.stars) r.stars = starsFor(r.score);
|
||||||
|
if (!r.promptTokensEst) r.promptTokensEst = r.promptChars ? Math.round(r.promptChars / 4) : 0;
|
||||||
|
return r;
|
||||||
|
});
|
||||||
|
const cls = r => (!r.error && r.testsPassed === r.testsTotal && r.testsTotal > 0) ? 'pass' : (r.testsTotal > 0 && r.testsPassed > 0) ? 'partial' : 'fail';
|
||||||
|
const pctBar = (passed, total, w=80) => {
|
||||||
|
if (total === 0) return '-';
|
||||||
|
const pct = passed/total*100;
|
||||||
|
const c = pct === 100 ? 'bar-fill' : 'bar-partial';
|
||||||
|
return `<span class="bar bar-bg" style="width:${w}px"><span class="bar ${c}" style="width:${Math.round(pct/100*w)}px"></span></span> ${passed}/${total}`;
|
||||||
|
};
|
||||||
|
|
||||||
|
// Meta
|
||||||
|
const totalTime = DATA.reduce((s,r) => s + r.totalDurationMs, 0);
|
||||||
|
document.getElementById('meta').textContent = `${new Date().toLocaleDateString('fi-FI')} — ${DATA.length} ajoa — ${(totalTime/1000/60).toFixed(1)} min`;
|
||||||
|
|
||||||
|
// Cards
|
||||||
|
const models = [...new Set(DATA.map(r => r.model))];
|
||||||
|
const scenarios = [...new Set(DATA.map(r => r.scenario))];
|
||||||
|
const avgScore = DATA.length ? Math.round(DATA.reduce((s,r) => s + r.score, 0) / DATA.length) : 0;
|
||||||
|
const totalPassed = DATA.reduce((s,r) => s + r.testsPassed, 0);
|
||||||
|
const totalTests = DATA.reduce((s,r) => s + r.testsTotal, 0);
|
||||||
|
const passRate = totalTests ? Math.round(totalPassed/totalTests*100) : 0;
|
||||||
|
const bestModel = models.map(m => {
|
||||||
|
const mrs = DATA.filter(r => r.model === m);
|
||||||
|
return { model: m, avg: Math.round(mrs.reduce((s,r) => s + r.score, 0) / mrs.length) };
|
||||||
|
}).sort((a,b) => b.avg - a.avg)[0];
|
||||||
|
const fastestModel = models.map(m => {
|
||||||
|
const mrs = DATA.filter(r => r.model === m);
|
||||||
|
return { model: m, speed: Math.round(mrs.reduce((s,r) => s + r.avgTokPerSec, 0) / mrs.length) };
|
||||||
|
}).sort((a,b) => b.speed - a.speed)[0];
|
||||||
|
|
||||||
|
document.getElementById('cards').innerHTML = `
|
||||||
|
<div class="card"><div class="label">Keskiarvo</div><div class="value">${starsFor(avgScore)}</div><div class="sub">${avgScore} pistetta</div></div>
|
||||||
|
<div class="card"><div class="label">Testien läpäisy</div><div class="value">${passRate}%</div><div class="sub">${totalPassed}/${totalTests} testiä</div></div>
|
||||||
|
<div class="card"><div class="label">Paras malli</div><div class="value" style="font-size:1.2rem">${bestModel?.model || '-'}</div><div class="sub">${bestModel?.avg || 0}p</div></div>
|
||||||
|
<div class="card"><div class="label">Nopein</div><div class="value" style="font-size:1.2rem">${fastestModel?.model || '-'}</div><div class="sub">${fastestModel?.speed || 0} tok/s</div></div>
|
||||||
|
<div class="card"><div class="label">Malleja</div><div class="value">${models.length}</div><div class="sub">${scenarios.length} skenaariota</div></div>
|
||||||
|
<div class="card"><div class="label">Kokonaisaika</div><div class="value">${(totalTime/1000/60).toFixed(1)}</div><div class="sub">minuuttia</div></div>
|
||||||
|
`;
|
||||||
|
|
||||||
|
// Summary table
|
||||||
|
const sumHead = document.querySelector('#summary-table thead');
|
||||||
|
const sumBody = document.querySelector('#summary-table tbody');
|
||||||
|
sumHead.innerHTML = '<tr><th>Malli</th>' + scenarios.map(s => `<th>${s}</th>`).join('') + '<th>Yht.</th><th>Out tok</th><th>Aika</th><th>tok/s</th><th>Pisteet</th></tr>';
|
||||||
|
|
||||||
|
const modelRows = models.map(m => {
|
||||||
|
const mrs = DATA.filter(r => r.model === m);
|
||||||
|
const tp = mrs.reduce((s,r) => s + r.testsPassed, 0);
|
||||||
|
const tt = mrs.reduce((s,r) => s + r.testsTotal, 0);
|
||||||
|
const tok = mrs.reduce((s,r) => s + r.totalTokens, 0);
|
||||||
|
const time = mrs.reduce((s,r) => s + r.totalDurationMs, 0);
|
||||||
|
const speed = Math.round(mrs.reduce((s,r) => s + r.avgTokPerSec, 0) / mrs.length);
|
||||||
|
const avg = Math.round(mrs.reduce((s,r) => s + r.score, 0) / mrs.length);
|
||||||
|
const scenCols = scenarios.map(s => {
|
||||||
|
const r = mrs.find(r => r.scenario === s);
|
||||||
|
if (!r) return '<td>-</td>';
|
||||||
|
return `<td class="${cls(r)}">${pctBar(r.testsPassed, r.testsTotal, 60)} <span style="color:var(--dim)">${(r.totalDurationMs/1000).toFixed(0)}s</span></td>`;
|
||||||
|
}).join('');
|
||||||
|
return { avg, html: `<tr><td class="model-name">${m}</td>${scenCols}<td>${pctBar(tp, tt)}</td><td>${(tok/1000).toFixed(1)}K</td><td>${(time/1000).toFixed(0)}s</td><td>${speed}</td><td><span class="stars">${starsFor(avg)}</span> ${avg}p</td></tr>` };
|
||||||
|
}).sort((a,b) => b.avg - a.avg);
|
||||||
|
sumBody.innerHTML = modelRows.map(r => r.html).join('');
|
||||||
|
|
||||||
|
// Results table
|
||||||
|
const resHead = document.querySelector('#results-table thead');
|
||||||
|
const resBody = document.querySelector('#results-table tbody');
|
||||||
|
const resCols = ['Malli','Skenaario','Speksi','Testit','Korjaus','Ctx','Out tok','Aika','tok/s','Pisteet'];
|
||||||
|
resHead.innerHTML = '<tr>' + resCols.map((c,i) => `<th data-col="${i}">${c}</th>`).join('') + '</tr>';
|
||||||
|
|
||||||
|
let sortCol = 9, sortAsc = false;
|
||||||
|
function renderResults() {
|
||||||
|
const sorted = [...DATA].sort((a,b) => {
|
||||||
|
const vals = [
|
||||||
|
[a.model, b.model],
|
||||||
|
[a.scenario, b.scenario],
|
||||||
|
[a.specEntities, b.specEntities],
|
||||||
|
[a.testsPassed/Math.max(a.testsTotal,1), b.testsPassed/Math.max(b.testsTotal,1)],
|
||||||
|
[a.fixRounds, b.fixRounds],
|
||||||
|
[a.promptTokensEst, b.promptTokensEst],
|
||||||
|
[a.totalTokens, b.totalTokens],
|
||||||
|
[a.totalDurationMs, b.totalDurationMs],
|
||||||
|
[a.avgTokPerSec, b.avgTokPerSec],
|
||||||
|
[a.score, b.score],
|
||||||
|
][sortCol];
|
||||||
|
const cmp = typeof vals[0] === 'string' ? vals[0].localeCompare(vals[1]) : vals[0] - vals[1];
|
||||||
|
return sortAsc ? cmp : -cmp;
|
||||||
|
});
|
||||||
|
resBody.innerHTML = sorted.map(r => {
|
||||||
|
const c = cls(r);
|
||||||
|
return `<tr>
|
||||||
|
<td class="model-name">${r.model}</td>
|
||||||
|
<td>${r.scenario}</td>
|
||||||
|
<td>${r.specOk ? `✓ ${r.specEntities}e` : '<span class="fail">✗</span>'}</td>
|
||||||
|
<td class="${c}">${pctBar(r.testsPassed, r.testsTotal)}</td>
|
||||||
|
<td>${r.fixRounds > 0 ? r.fixRounds + '×' : '-'}</td>
|
||||||
|
<td>${r.promptTokensEst > 0 ? '~'+(r.promptTokensEst/1000).toFixed(1)+'K' : '-'}</td>
|
||||||
|
<td>${r.totalTokens > 0 ? (r.totalTokens/1000).toFixed(1)+'K' : '-'}</td>
|
||||||
|
<td>${(r.totalDurationMs/1000).toFixed(0)}s</td>
|
||||||
|
<td>${r.avgTokPerSec.toFixed(0)}</td>
|
||||||
|
<td><span class="stars">${r.stars}</span> ${r.score}p</td>
|
||||||
|
</tr>`;
|
||||||
|
}).join('');
|
||||||
|
document.querySelectorAll('#results-table th').forEach((th,i) => {
|
||||||
|
th.className = i === sortCol ? (sortAsc ? 'sorted-asc' : 'sorted-desc') : '';
|
||||||
|
});
|
||||||
|
}
|
||||||
|
document.querySelector('#results-table thead').addEventListener('click', e => {
|
||||||
|
const col = parseInt(e.target.dataset.col);
|
||||||
|
if (isNaN(col)) return;
|
||||||
|
if (sortCol === col) sortAsc = !sortAsc;
|
||||||
|
else { sortCol = col; sortAsc = false; }
|
||||||
|
renderResults();
|
||||||
|
});
|
||||||
|
renderResults();
|
||||||
|
</script>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
117
kipina-codebench/results/2026-04-14T11-15.json
Normal file
117
kipina-codebench/results/2026-04-14T11-15.json
Normal file
@@ -0,0 +1,117 @@
|
|||||||
|
[
|
||||||
|
{
|
||||||
|
"model": "qwen3:8b",
|
||||||
|
"scenario": "blog",
|
||||||
|
"reqOk": true,
|
||||||
|
"specOk": true,
|
||||||
|
"specEntities": 1,
|
||||||
|
"validationIssues": 0,
|
||||||
|
"fixRounds": 3,
|
||||||
|
"testsTotal": 11,
|
||||||
|
"testsPassed": 9,
|
||||||
|
"testsFailed": 2,
|
||||||
|
"totalDurationMs": 75178,
|
||||||
|
"totalTokens": 9916,
|
||||||
|
"avgTokPerSec": 142.94675043471062,
|
||||||
|
"promptChars": 10516,
|
||||||
|
"promptTokensEst": 2629,
|
||||||
|
"score": 69,
|
||||||
|
"stars": "★★★☆☆",
|
||||||
|
"error": null,
|
||||||
|
"profile": "small",
|
||||||
|
"promptName": "code-small",
|
||||||
|
"round": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"model": "qwen3:8b",
|
||||||
|
"scenario": "blog",
|
||||||
|
"reqOk": true,
|
||||||
|
"specOk": true,
|
||||||
|
"specEntities": 2,
|
||||||
|
"validationIssues": 1,
|
||||||
|
"fixRounds": 5,
|
||||||
|
"testsTotal": 0,
|
||||||
|
"testsPassed": 0,
|
||||||
|
"testsFailed": 0,
|
||||||
|
"totalDurationMs": 98787,
|
||||||
|
"totalTokens": 12904,
|
||||||
|
"avgTokPerSec": 141.16873850064812,
|
||||||
|
"promptChars": 11810,
|
||||||
|
"promptTokensEst": 2953,
|
||||||
|
"score": 0,
|
||||||
|
"stars": "☆☆☆☆☆",
|
||||||
|
"error": "Testit kaatuivat",
|
||||||
|
"profile": "small",
|
||||||
|
"promptName": "code-small",
|
||||||
|
"round": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"model": "qwen3:8b",
|
||||||
|
"scenario": "blog",
|
||||||
|
"reqOk": true,
|
||||||
|
"specOk": true,
|
||||||
|
"specEntities": 2,
|
||||||
|
"validationIssues": 0,
|
||||||
|
"fixRounds": 3,
|
||||||
|
"testsTotal": 1,
|
||||||
|
"testsPassed": 0,
|
||||||
|
"testsFailed": 1,
|
||||||
|
"totalDurationMs": 81763,
|
||||||
|
"totalTokens": 10277,
|
||||||
|
"avgTokPerSec": 134.82946940948588,
|
||||||
|
"promptChars": 11534,
|
||||||
|
"promptTokensEst": 2884,
|
||||||
|
"score": 20,
|
||||||
|
"stars": "★☆☆☆☆",
|
||||||
|
"error": "Syntaksivirhe",
|
||||||
|
"profile": "small",
|
||||||
|
"promptName": "code-small",
|
||||||
|
"round": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"model": "qwen3:8b",
|
||||||
|
"scenario": "blog",
|
||||||
|
"reqOk": true,
|
||||||
|
"specOk": true,
|
||||||
|
"specEntities": 1,
|
||||||
|
"validationIssues": 0,
|
||||||
|
"fixRounds": 3,
|
||||||
|
"testsTotal": 1,
|
||||||
|
"testsPassed": 0,
|
||||||
|
"testsFailed": 1,
|
||||||
|
"totalDurationMs": 88517,
|
||||||
|
"totalTokens": 11280,
|
||||||
|
"avgTokPerSec": 136.63597159351744,
|
||||||
|
"promptChars": 10568,
|
||||||
|
"promptTokensEst": 2642,
|
||||||
|
"score": 20,
|
||||||
|
"stars": "★☆☆☆☆",
|
||||||
|
"error": "Syntaksivirhe",
|
||||||
|
"profile": "small",
|
||||||
|
"promptName": "code-small",
|
||||||
|
"round": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"model": "qwen3:8b",
|
||||||
|
"scenario": "blog",
|
||||||
|
"reqOk": true,
|
||||||
|
"specOk": true,
|
||||||
|
"specEntities": 2,
|
||||||
|
"validationIssues": 0,
|
||||||
|
"fixRounds": 3,
|
||||||
|
"testsTotal": 12,
|
||||||
|
"testsPassed": 9,
|
||||||
|
"testsFailed": 3,
|
||||||
|
"totalDurationMs": 87817,
|
||||||
|
"totalTokens": 11171,
|
||||||
|
"avgTokPerSec": 136.1538785139482,
|
||||||
|
"promptChars": 11627,
|
||||||
|
"promptTokensEst": 2907,
|
||||||
|
"score": 65,
|
||||||
|
"stars": "★★★☆☆",
|
||||||
|
"error": null,
|
||||||
|
"profile": "small",
|
||||||
|
"promptName": "code-small",
|
||||||
|
"round": 5
|
||||||
|
}
|
||||||
|
]
|
||||||
Reference in New Issue
Block a user