From 2d1b1d3ec6d2c5637933ca71c2dba10383a23768 Mon Sep 17 00:00:00 2001
From: jaakko <jaakko@kipina.tech>
Date: Wed, 15 Apr 2026 13:14:39 +0300
Subject: [PATCH] initial commit: agentic office

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 .../results/2026-04-14T19-58-38.html          | 183 +++++++++++++++
 .../results/2026-04-14T19-58-38.json          |  71 ++++++
 .../results/2026-04-14T20-19-09.html          | 183 +++++++++++++++
 .../results/2026-04-14T20-19-09.json          |   1 +
 .../results/2026-04-14T20-24-36.html          | 183 +++++++++++++++
 .../results/2026-04-14T20-24-36.json          |   1 +
 .../results/2026-04-14T20-32-12.html          | 183 +++++++++++++++
 .../results/2026-04-14T20-32-12.json          |  65 ++++++
 .../results/2026-04-14T20-37-18.html          | 183 +++++++++++++++
 .../results/2026-04-14T20-37-18.json          |  71 ++++++
 .../results/2026-04-14T20-41-39.html          | 183 +++++++++++++++
 .../results/2026-04-14T20-41-39.json          |   1 +
 .../results/2026-04-14T20-41-48.html          | 183 +++++++++++++++
 .../results/2026-04-14T20-41-48.json          |   1 +
 .../results/2026-04-14T20-41-56.html          | 183 +++++++++++++++
 .../results/2026-04-14T20-41-56.json          |   1 +
 .../results/2026-04-14T20-42-21.html          | 183 +++++++++++++++
 .../results/2026-04-14T20-42-21.json          |   1 +
 .../results/2026-04-14T21-15-46.html          | 183 +++++++++++++++
 .../results/2026-04-14T21-15-46.json          |   1 +
 .../results/2026-04-14T21-40-58.html          | 183 +++++++++++++++
 .../results/2026-04-14T21-40-58.json          | 209 ++++++++++++++++++
 .../results/2026-04-14T21-50-37.html          | 183 +++++++++++++++
 .../results/2026-04-14T21-50-37.json          |   1 +
 .../results/2026-04-14T21-50-42.html          | 183 +++++++++++++++
 .../results/2026-04-14T21-50-42.json          |   1 +
 network-poc/frontend/public/GUIDE.md          |   2 +-
 network-poc/native-node/src/tui.rs            |   9 +-
 28 files changed, 2811 insertions(+), 4 deletions(-)
 create mode 100644 kipina-codebench/results/2026-04-14T19-58-38.html
 create mode 100644 kipina-codebench/results/2026-04-14T19-58-38.json
 create mode 100644 kipina-codebench/results/2026-04-14T20-19-09.html
 create mode 100644 kipina-codebench/results/2026-04-14T20-19-09.json
 create mode 100644 kipina-codebench/results/2026-04-14T20-24-36.html
 create mode 100644 kipina-codebench/results/2026-04-14T20-24-36.json
 create mode 100644 kipina-codebench/results/2026-04-14T20-32-12.html
 create mode 100644 kipina-codebench/results/2026-04-14T20-32-12.json
 create mode 100644 kipina-codebench/results/2026-04-14T20-37-18.html
 create mode 100644 kipina-codebench/results/2026-04-14T20-37-18.json
 create mode 100644 kipina-codebench/results/2026-04-14T20-41-39.html
 create mode 100644 kipina-codebench/results/2026-04-14T20-41-39.json
 create mode 100644 kipina-codebench/results/2026-04-14T20-41-48.html
 create mode 100644 kipina-codebench/results/2026-04-14T20-41-48.json
 create mode 100644 kipina-codebench/results/2026-04-14T20-41-56.html
 create mode 100644 kipina-codebench/results/2026-04-14T20-41-56.json
 create mode 100644 kipina-codebench/results/2026-04-14T20-42-21.html
 create mode 100644 kipina-codebench/results/2026-04-14T20-42-21.json
 create mode 100644 kipina-codebench/results/2026-04-14T21-15-46.html
 create mode 100644 kipina-codebench/results/2026-04-14T21-15-46.json
 create mode 100644 kipina-codebench/results/2026-04-14T21-40-58.html
 create mode 100644 kipina-codebench/results/2026-04-14T21-40-58.json
 create mode 100644 kipina-codebench/results/2026-04-14T21-50-37.html
 create mode 100644 kipina-codebench/results/2026-04-14T21-50-37.json
 create mode 100644 kipina-codebench/results/2026-04-14T21-50-42.html
 create mode 100644 kipina-codebench/results/2026-04-14T21-50-42.json

diff --git a/kipina-codebench/results/2026-04-14T19-58-38.html b/kipina-codebench/results/2026-04-14T19-58-38.html
new file mode 100644
index 0000000..8d08d42
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T19-58-38.html
@@ -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":0,"testsTotal":0,"testsPassed":0,"testsFailed":0,"totalDurationMs":31870,"totalTokens":4024,"avgTokPerSec":143.80989267612117,"promptChars":11168,"promptTokensEst":2792,"score":40,"stars":"★★☆☆☆","error":null,"profile":"small","promptName":"code-go","round":1},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":0,"testsTotal":0,"testsPassed":0,"testsFailed":0,"totalDurationMs":50050,"totalTokens":6218,"avgTokPerSec":142.0357712618218,"promptChars":11624,"promptTokensEst":2906,"score":40,"stars":"★★☆☆☆","error":null,"profile":"small","promptName":"code-go","round":2},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":0,"testsTotal":0,"testsPassed":0,"testsFailed":0,"totalDurationMs":45209,"totalTokens":5571,"avgTokPerSec":139.512254185898,"promptChars":11544,"promptTokensEst":2886,"score":40,"stars":"★★☆☆☆","error":null,"profile":"small","promptName":"code-go","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>
diff --git a/kipina-codebench/results/2026-04-14T19-58-38.json b/kipina-codebench/results/2026-04-14T19-58-38.json
new file mode 100644
index 0000000..529670d
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T19-58-38.json
@@ -0,0 +1,71 @@
+[
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 31870,
+    "totalTokens": 4024,
+    "avgTokPerSec": 143.80989267612117,
+    "promptChars": 11168,
+    "promptTokensEst": 2792,
+    "score": 40,
+    "stars": "★★☆☆☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-go",
+    "round": 1
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 50050,
+    "totalTokens": 6218,
+    "avgTokPerSec": 142.0357712618218,
+    "promptChars": 11624,
+    "promptTokensEst": 2906,
+    "score": 40,
+    "stars": "★★☆☆☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-go",
+    "round": 2
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 45209,
+    "totalTokens": 5571,
+    "avgTokPerSec": 139.512254185898,
+    "promptChars": 11544,
+    "promptTokensEst": 2886,
+    "score": 40,
+    "stars": "★★☆☆☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-go",
+    "round": 3
+  }
+]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T20-19-09.html b/kipina-codebench/results/2026-04-14T20-19-09.html
new file mode 100644
index 0000000..b7b16cf
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-19-09.html
@@ -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 = [];
+
+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>
diff --git a/kipina-codebench/results/2026-04-14T20-19-09.json b/kipina-codebench/results/2026-04-14T20-19-09.json
new file mode 100644
index 0000000..0637a08
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-19-09.json
@@ -0,0 +1 @@
+[]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T20-24-36.html b/kipina-codebench/results/2026-04-14T20-24-36.html
new file mode 100644
index 0000000..b7b16cf
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-24-36.html
@@ -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 = [];
+
+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>
diff --git a/kipina-codebench/results/2026-04-14T20-24-36.json b/kipina-codebench/results/2026-04-14T20-24-36.json
new file mode 100644
index 0000000..0637a08
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-24-36.json
@@ -0,0 +1 @@
+[]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T20-32-12.html b/kipina-codebench/results/2026-04-14T20-32-12.html
new file mode 100644
index 0000000..2084207
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-32-12.html
@@ -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":0,"testsTotal":0,"testsPassed":0,"testsFailed":0,"totalDurationMs":0,"totalTokens":0,"avgTokPerSec":0,"promptChars":30421,"promptTokensEst":7605,"score":0,"stars":"","error":"Puuttuvat: go.mod","round":1},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":0,"testsTotal":0,"testsPassed":0,"testsFailed":0,"totalDurationMs":0,"totalTokens":0,"avgTokPerSec":0,"promptChars":26971,"promptTokensEst":6743,"score":0,"stars":"","error":"Puuttuvat: go.mod","round":2},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":0,"testsTotal":0,"testsPassed":0,"testsFailed":0,"totalDurationMs":0,"totalTokens":0,"avgTokPerSec":0,"promptChars":27694,"promptTokensEst":6924,"score":0,"stars":"","error":"Puuttuvat: go.mod","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>
diff --git a/kipina-codebench/results/2026-04-14T20-32-12.json b/kipina-codebench/results/2026-04-14T20-32-12.json
new file mode 100644
index 0000000..8c8747d
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-32-12.json
@@ -0,0 +1,65 @@
+[
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 0,
+    "totalTokens": 0,
+    "avgTokPerSec": 0,
+    "promptChars": 30421,
+    "promptTokensEst": 7605,
+    "score": 0,
+    "stars": "",
+    "error": "Puuttuvat: go.mod",
+    "round": 1
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 0,
+    "totalTokens": 0,
+    "avgTokPerSec": 0,
+    "promptChars": 26971,
+    "promptTokensEst": 6743,
+    "score": 0,
+    "stars": "",
+    "error": "Puuttuvat: go.mod",
+    "round": 2
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 0,
+    "totalTokens": 0,
+    "avgTokPerSec": 0,
+    "promptChars": 27694,
+    "promptTokensEst": 6924,
+    "score": 0,
+    "stars": "",
+    "error": "Puuttuvat: go.mod",
+    "round": 3
+  }
+]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T20-37-18.html b/kipina-codebench/results/2026-04-14T20-37-18.html
new file mode 100644
index 0000000..c09467e
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-37-18.html
@@ -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":1,"testsTotal":0,"testsPassed":0,"testsFailed":0,"totalDurationMs":95709,"totalTokens":11690,"avgTokPerSec":132.16841505518815,"promptChars":20579,"promptTokensEst":5145,"score":30,"stars":"★★☆☆☆","error":null,"profile":"small","promptName":"code-go","round":1},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":0,"testsTotal":0,"testsPassed":0,"testsFailed":0,"totalDurationMs":45562,"totalTokens":5534,"avgTokPerSec":132.0768897820692,"promptChars":19628,"promptTokensEst":4907,"score":40,"stars":"★★☆☆☆","error":null,"profile":"small","promptName":"code-go","round":2},{"model":"qwen3:8b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":0,"testsTotal":0,"testsPassed":0,"testsFailed":0,"totalDurationMs":47588,"totalTokens":5819,"avgTokPerSec":132.74582771351155,"promptChars":20752,"promptTokensEst":5188,"score":40,"stars":"★★☆☆☆","error":null,"profile":"small","promptName":"code-go","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>
diff --git a/kipina-codebench/results/2026-04-14T20-37-18.json b/kipina-codebench/results/2026-04-14T20-37-18.json
new file mode 100644
index 0000000..a250f51
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-37-18.json
@@ -0,0 +1,71 @@
+[
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 1,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 95709,
+    "totalTokens": 11690,
+    "avgTokPerSec": 132.16841505518815,
+    "promptChars": 20579,
+    "promptTokensEst": 5145,
+    "score": 30,
+    "stars": "★★☆☆☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-go",
+    "round": 1
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 45562,
+    "totalTokens": 5534,
+    "avgTokPerSec": 132.0768897820692,
+    "promptChars": 19628,
+    "promptTokensEst": 4907,
+    "score": 40,
+    "stars": "★★☆☆☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-go",
+    "round": 2
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 47588,
+    "totalTokens": 5819,
+    "avgTokPerSec": 132.74582771351155,
+    "promptChars": 20752,
+    "promptTokensEst": 5188,
+    "score": 40,
+    "stars": "★★☆☆☆",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-go",
+    "round": 3
+  }
+]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T20-41-39.html b/kipina-codebench/results/2026-04-14T20-41-39.html
new file mode 100644
index 0000000..b7b16cf
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-41-39.html
@@ -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 = [];
+
+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>
diff --git a/kipina-codebench/results/2026-04-14T20-41-39.json b/kipina-codebench/results/2026-04-14T20-41-39.json
new file mode 100644
index 0000000..0637a08
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-41-39.json
@@ -0,0 +1 @@
+[]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T20-41-48.html b/kipina-codebench/results/2026-04-14T20-41-48.html
new file mode 100644
index 0000000..b7b16cf
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-41-48.html
@@ -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 = [];
+
+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>
diff --git a/kipina-codebench/results/2026-04-14T20-41-48.json b/kipina-codebench/results/2026-04-14T20-41-48.json
new file mode 100644
index 0000000..0637a08
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-41-48.json
@@ -0,0 +1 @@
+[]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T20-41-56.html b/kipina-codebench/results/2026-04-14T20-41-56.html
new file mode 100644
index 0000000..b7b16cf
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-41-56.html
@@ -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 = [];
+
+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>
diff --git a/kipina-codebench/results/2026-04-14T20-41-56.json b/kipina-codebench/results/2026-04-14T20-41-56.json
new file mode 100644
index 0000000..0637a08
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-41-56.json
@@ -0,0 +1 @@
+[]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T20-42-21.html b/kipina-codebench/results/2026-04-14T20-42-21.html
new file mode 100644
index 0000000..b7b16cf
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-42-21.html
@@ -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 = [];
+
+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>
diff --git a/kipina-codebench/results/2026-04-14T20-42-21.json b/kipina-codebench/results/2026-04-14T20-42-21.json
new file mode 100644
index 0000000..0637a08
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T20-42-21.json
@@ -0,0 +1 @@
+[]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T21-15-46.html b/kipina-codebench/results/2026-04-14T21-15-46.html
new file mode 100644
index 0000000..b7b16cf
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T21-15-46.html
@@ -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 = [];
+
+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>
diff --git a/kipina-codebench/results/2026-04-14T21-15-46.json b/kipina-codebench/results/2026-04-14T21-15-46.json
new file mode 100644
index 0000000..0637a08
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T21-15-46.json
@@ -0,0 +1 @@
+[]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T21-40-58.html b/kipina-codebench/results/2026-04-14T21-40-58.html
new file mode 100644
index 0000000..d3932f2
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T21-40-58.html
@@ -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-coder:30b","scenario":"todo","reqOk":true,"specOk":true,"specEntities":1,"validationIssues":0,"fixRounds":0,"testsTotal":6,"testsPassed":6,"testsFailed":0,"totalDurationMs":18254,"totalTokens":2677,"avgTokPerSec":189.94573063405974,"promptChars":12393,"promptTokensEst":3098,"score":100,"stars":"★★★★★","error":null,"profile":"large","promptName":"code","round":1},{"model":"qwen3-coder:30b","scenario":"users","reqOk":true,"specOk":true,"specEntities":1,"validationIssues":0,"fixRounds":3,"testsTotal":8,"testsPassed":7,"testsFailed":1,"totalDurationMs":62436,"totalTokens":10254,"avgTokPerSec":180.7144707287582,"promptChars":12114,"promptTokensEst":3029,"score":73,"stars":"★★★★☆","error":null,"profile":"large","promptName":"code","round":1},{"model":"qwen3-coder:30b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":0,"testsTotal":12,"testsPassed":12,"testsFailed":0,"totalDurationMs":31205,"totalTokens":5060,"avgTokPerSec":184.0318504412911,"promptChars":12363,"promptTokensEst":3091,"score":100,"stars":"★★★★★","error":null,"profile":"large","promptName":"code","round":1},{"model":"qwen3-coder:30b","scenario":"todo","reqOk":true,"specOk":true,"specEntities":1,"validationIssues":0,"fixRounds":2,"testsTotal":6,"testsPassed":6,"testsFailed":0,"totalDurationMs":33675,"totalTokens":5292,"avgTokPerSec":187.55877092211753,"promptChars":12030,"promptTokensEst":3008,"score":80,"stars":"★★★★☆","error":null,"profile":"large","promptName":"code","round":2},{"model":"qwen3-coder:30b","scenario":"users","reqOk":true,"specOk":true,"specEntities":1,"validationIssues":0,"fixRounds":0,"testsTotal":6,"testsPassed":6,"testsFailed":0,"totalDurationMs":17703,"totalTokens":2890,"avgTokPerSec":185.61718567437205,"promptChars":12222,"promptTokensEst":3056,"score":100,"stars":"★★★★★","error":null,"profile":"large","promptName":"code","round":2},{"model":"qwen3-coder:30b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":1,"testsTotal":12,"testsPassed":12,"testsFailed":0,"totalDurationMs":48697,"totalTokens":7851,"avgTokPerSec":181.3588176072106,"promptChars":12618,"promptTokensEst":3155,"score":90,"stars":"★★★★★","error":null,"profile":"large","promptName":"code","round":2},{"model":"qwen3-coder:30b","scenario":"todo","reqOk":true,"specOk":true,"specEntities":1,"validationIssues":0,"fixRounds":0,"testsTotal":6,"testsPassed":6,"testsFailed":0,"totalDurationMs":17426,"totalTokens":2532,"avgTokPerSec":189.99848651835183,"promptChars":12217,"promptTokensEst":3054,"score":100,"stars":"★★★★★","error":null,"profile":"large","promptName":"code","round":3},{"model":"qwen3-coder:30b","scenario":"users","reqOk":true,"specOk":true,"specEntities":1,"validationIssues":0,"fixRounds":3,"testsTotal":9,"testsPassed":8,"testsFailed":1,"totalDurationMs":51361,"totalTokens":8528,"avgTokPerSec":183.31274532724456,"promptChars":11465,"promptTokensEst":2866,"score":73,"stars":"★★★★☆","error":null,"profile":"large","promptName":"code","round":3},{"model":"qwen3-coder:30b","scenario":"blog","reqOk":true,"specOk":true,"specEntities":2,"validationIssues":0,"fixRounds":1,"testsTotal":12,"testsPassed":12,"testsFailed":0,"totalDurationMs":49147,"totalTokens":7931,"avgTokPerSec":178.9319278594721,"promptChars":12262,"promptTokensEst":3066,"score":90,"stars":"★★★★★","error":null,"profile":"large","promptName":"code","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>
diff --git a/kipina-codebench/results/2026-04-14T21-40-58.json b/kipina-codebench/results/2026-04-14T21-40-58.json
new file mode 100644
index 0000000..36d5308
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T21-40-58.json
@@ -0,0 +1,209 @@
+[
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "todo",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 6,
+    "testsPassed": 6,
+    "testsFailed": 0,
+    "totalDurationMs": 18254,
+    "totalTokens": 2677,
+    "avgTokPerSec": 189.94573063405974,
+    "promptChars": 12393,
+    "promptTokensEst": 3098,
+    "score": 100,
+    "stars": "★★★★★",
+    "error": null,
+    "profile": "large",
+    "promptName": "code",
+    "round": 1
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "users",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 8,
+    "testsPassed": 7,
+    "testsFailed": 1,
+    "totalDurationMs": 62436,
+    "totalTokens": 10254,
+    "avgTokPerSec": 180.7144707287582,
+    "promptChars": 12114,
+    "promptTokensEst": 3029,
+    "score": 73,
+    "stars": "★★★★☆",
+    "error": null,
+    "profile": "large",
+    "promptName": "code",
+    "round": 1
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 12,
+    "testsPassed": 12,
+    "testsFailed": 0,
+    "totalDurationMs": 31205,
+    "totalTokens": 5060,
+    "avgTokPerSec": 184.0318504412911,
+    "promptChars": 12363,
+    "promptTokensEst": 3091,
+    "score": 100,
+    "stars": "★★★★★",
+    "error": null,
+    "profile": "large",
+    "promptName": "code",
+    "round": 1
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "todo",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 2,
+    "testsTotal": 6,
+    "testsPassed": 6,
+    "testsFailed": 0,
+    "totalDurationMs": 33675,
+    "totalTokens": 5292,
+    "avgTokPerSec": 187.55877092211753,
+    "promptChars": 12030,
+    "promptTokensEst": 3008,
+    "score": 80,
+    "stars": "★★★★☆",
+    "error": null,
+    "profile": "large",
+    "promptName": "code",
+    "round": 2
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "users",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 6,
+    "testsPassed": 6,
+    "testsFailed": 0,
+    "totalDurationMs": 17703,
+    "totalTokens": 2890,
+    "avgTokPerSec": 185.61718567437205,
+    "promptChars": 12222,
+    "promptTokensEst": 3056,
+    "score": 100,
+    "stars": "★★★★★",
+    "error": null,
+    "profile": "large",
+    "promptName": "code",
+    "round": 2
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 1,
+    "testsTotal": 12,
+    "testsPassed": 12,
+    "testsFailed": 0,
+    "totalDurationMs": 48697,
+    "totalTokens": 7851,
+    "avgTokPerSec": 181.3588176072106,
+    "promptChars": 12618,
+    "promptTokensEst": 3155,
+    "score": 90,
+    "stars": "★★★★★",
+    "error": null,
+    "profile": "large",
+    "promptName": "code",
+    "round": 2
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "todo",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 6,
+    "testsPassed": 6,
+    "testsFailed": 0,
+    "totalDurationMs": 17426,
+    "totalTokens": 2532,
+    "avgTokPerSec": 189.99848651835183,
+    "promptChars": 12217,
+    "promptTokensEst": 3054,
+    "score": 100,
+    "stars": "★★★★★",
+    "error": null,
+    "profile": "large",
+    "promptName": "code",
+    "round": 3
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "users",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 1,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 9,
+    "testsPassed": 8,
+    "testsFailed": 1,
+    "totalDurationMs": 51361,
+    "totalTokens": 8528,
+    "avgTokPerSec": 183.31274532724456,
+    "promptChars": 11465,
+    "promptTokensEst": 2866,
+    "score": 73,
+    "stars": "★★★★☆",
+    "error": null,
+    "profile": "large",
+    "promptName": "code",
+    "round": 3
+  },
+  {
+    "model": "qwen3-coder:30b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 1,
+    "testsTotal": 12,
+    "testsPassed": 12,
+    "testsFailed": 0,
+    "totalDurationMs": 49147,
+    "totalTokens": 7931,
+    "avgTokPerSec": 178.9319278594721,
+    "promptChars": 12262,
+    "promptTokensEst": 3066,
+    "score": 90,
+    "stars": "★★★★★",
+    "error": null,
+    "profile": "large",
+    "promptName": "code",
+    "round": 3
+  }
+]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T21-50-37.html b/kipina-codebench/results/2026-04-14T21-50-37.html
new file mode 100644
index 0000000..b7b16cf
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T21-50-37.html
@@ -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 = [];
+
+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>
diff --git a/kipina-codebench/results/2026-04-14T21-50-37.json b/kipina-codebench/results/2026-04-14T21-50-37.json
new file mode 100644
index 0000000..0637a08
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T21-50-37.json
@@ -0,0 +1 @@
+[]
\ No newline at end of file
diff --git a/kipina-codebench/results/2026-04-14T21-50-42.html b/kipina-codebench/results/2026-04-14T21-50-42.html
new file mode 100644
index 0000000..b7b16cf
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T21-50-42.html
@@ -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 = [];
+
+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>
diff --git a/kipina-codebench/results/2026-04-14T21-50-42.json b/kipina-codebench/results/2026-04-14T21-50-42.json
new file mode 100644
index 0000000..0637a08
--- /dev/null
+++ b/kipina-codebench/results/2026-04-14T21-50-42.json
@@ -0,0 +1 @@
+[]
\ No newline at end of file
diff --git a/network-poc/frontend/public/GUIDE.md b/network-poc/frontend/public/GUIDE.md
index 39e3092..e5de3f6 100644
--- a/network-poc/frontend/public/GUIDE.md
+++ b/network-poc/frontend/public/GUIDE.md
@@ -90,7 +90,7 @@ flowchart TD
     S["System prompt<br/><i>You are a coding assistant. Respond with ONLY code.</i><br/>🔒 Kiinteä, kovakoodattu — malli priorisoi tämän"]
     A["Agent prompt<br/><i>Olet kokenut ohjelmistokehittäjä...</i><br/>✏️ Käyttäjän muokattavissa UI:ssa"]
     U["User prompt<br/><i>Write ONLY the file main.py...</i><br/>📋 Vaihtelee joka kutsussa, sisältää kontekstin"]
-    P["Prefill: ``` <br/>🎯 Pakottaa mallin aloittamaan koodilla"]
+    P["Prefill: &#96;&#96;&#96; <br/>🎯 Pakottaa mallin aloittamaan koodilla"]
     S --> A --> U --> P
     P -->|malli jatkaa| R["Generoitu koodi"]
 
diff --git a/network-poc/native-node/src/tui.rs b/network-poc/native-node/src/tui.rs
index b0c1df8..ab8c1f4 100644
--- a/network-poc/native-node/src/tui.rs
+++ b/network-poc/native-node/src/tui.rs
@@ -46,9 +46,10 @@ pub async fn select_model(ollama_url: &str, client: &Client) -> Result<String, S
             return Err("Mallin nimi ei voi olla tyhjä".to_string());
         }
         
-        println!("  Ladataan malleja taustalla... Tämä voi kestää hetken ({})", new_model);
-        // Odotetaan että pull on valmis
-        let pull_body = serde_json::json!({ "name": &new_model });
+        println!("  Ladataan mallia {}... (Tämä voi kestää isojen mallien kohdalla pitkään, älä sulje ohjelmaa.)", new_model);
+        
+        // Odotetaan että pull on valmis, estetään stream jolloin yhteys pysyy auki latauksen loppuun
+        let pull_body = serde_json::json!({ "name": &new_model, "stream": false });
         let resp = client.post(&format!("{}/api/pull", ollama_url))
             .json(&pull_body)
             .send()
@@ -56,6 +57,8 @@ pub async fn select_model(ollama_url: &str, client: &Client) -> Result<String, S
             .map_err(|e| format!("Pull req virhe: {}", e))?;
             
         if resp.status().is_success() {
+            // Varmistetaan, että vastaus luetaan kokonaan loppuun ennen kuin jatketaan
+            let _ = resp.text().await.map_err(|e| format!("Vastauksen lukuvirhe: {}", e))?;
             println!("  ✓ Malli {} ladattu onnistuneesti!", new_model);
             return Ok(new_model);
         } else {