mirror of
https://github.com/Nutlope/hallmark.git
synced 2026-08-14 12:35:33 +02:00
- five-themes cards open a complete full-page mockup per theme - before/after cards open the actual generated pages (before from hallmark-lab, after from the eval runs), copied into _proposals/pages - eval judge defaults to operator mode: no Anthropic key spend, the Claude Code operator scores from the screenshots; --provider together or anthropic for an automated pass
339 lines
23 KiB
HTML
339 lines
23 KiB
HTML
<!doctype html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="utf-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
|
<title>Hallmark eval matrix</title>
|
|
<style>
|
|
:root{--bg:#101014;--panel:#17171d;--panel2:#1d1d25;--line:#2a2a34;--ink:#e8e8ee;--mute:#8b8b98;--good:#4cc38a;--bad:#e5484d;--warn:#d8a03d;--acc:#8a8af0}
|
|
*{box-sizing:border-box;margin:0;padding:0}
|
|
body{background:var(--bg);color:var(--ink);font:15px/1.5 system-ui,-apple-system,sans-serif;padding:2.5rem clamp(1rem,4vw,3rem) 5rem}
|
|
h1{font-size:1.6rem;letter-spacing:-.01em}
|
|
.sub{color:var(--mute);margin:.35rem 0 2rem;font-size:.9rem}
|
|
table.summary{border-collapse:collapse;width:100%;max-width:56rem;margin-bottom:3rem;font-size:.86rem;font-variant-numeric:tabular-nums}
|
|
.summary th,.summary td{text-align:left;padding:.5rem .8rem;border-bottom:1px solid var(--line)}
|
|
.summary th{color:var(--mute);font-weight:600;font-size:.72rem;text-transform:uppercase;letter-spacing:.08em}
|
|
.summary tr.base td{background:var(--panel)}
|
|
.tag{font-size:.64rem;text-transform:uppercase;letter-spacing:.08em;color:var(--acc);border:1px solid var(--acc);border-radius:999px;padding:.1rem .45rem;margin-left:.4rem}
|
|
.pack{color:var(--mute);font-size:.78em;margin-left:.45rem}
|
|
.delta{font-size:.78em;margin-left:.3rem}
|
|
.delta.up{color:var(--good)}.delta.down{color:var(--bad)}.delta.same{color:var(--mute)}
|
|
.brief{margin-bottom:3.2rem}
|
|
.brief h2{font-size:1.05rem;margin-bottom:.2rem}
|
|
.bname{color:var(--mute);font-weight:400}
|
|
.btext{color:var(--ink);opacity:.85;font-size:.9rem;max-width:60rem}
|
|
.bexpect{color:var(--mute);font-size:.78rem;margin:.2rem 0 1rem;max-width:60rem}
|
|
.grid{display:grid;grid-template-columns:repeat(auto-fill,minmax(300px,1fr));gap:1rem}
|
|
.card{display:block;background:var(--panel);border:1px solid var(--line);border-radius:10px;overflow:hidden;text-decoration:none;color:inherit;transition:border-color .15s ease,transform .15s ease}
|
|
.card:hover{border-color:var(--acc);transform:translateY(-2px)}
|
|
.thumb{aspect-ratio:16/10;background:var(--panel2);overflow:hidden}
|
|
.thumb img{width:100%;height:100%;object-fit:cover;object-position:left top;display:block}
|
|
.noshot{width:100%;height:100%;display:flex;align-items:center;justify-content:center;color:var(--mute);font-size:.8rem}
|
|
.meta{padding:.7rem .8rem .8rem;border-top:1px solid var(--line)}
|
|
.arm{font-weight:600;font-size:.86rem;margin-bottom:.45rem}
|
|
.chips{display:flex;flex-wrap:wrap;gap:.35rem}
|
|
.chip{font-size:.68rem;padding:.2rem .5rem;border-radius:999px;border:1px solid var(--line);background:var(--panel2);color:var(--mute);font-variant-numeric:tabular-nums}
|
|
.chip.good{color:var(--good);border-color:color-mix(in srgb,var(--good) 40%,var(--line))}
|
|
.chip.bad{color:var(--bad);border-color:color-mix(in srgb,var(--bad) 40%,var(--line))}
|
|
.chip.warn{color:var(--warn);border-color:color-mix(in srgb,var(--warn) 40%,var(--line))}
|
|
.chip.judge{color:var(--acc);border-color:color-mix(in srgb,var(--acc) 40%,var(--line))}
|
|
.empty{color:var(--mute);font-size:.85rem;padding:.6rem 0}
|
|
@media (prefers-reduced-motion:reduce){.card,.card:hover{transition:none;transform:none}}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<h1>Hallmark eval matrix</h1>
|
|
<p class="sub">Generated 2026-07-24T09:15:56.798Z · 30 run cells · click a card to open the artifact</p>
|
|
<table class="summary">
|
|
<thead><tr><th>arm</th><th>artifacts</th><th>mean FAILs</th><th>floor clean</th><th>judge mean</th></tr></thead>
|
|
<tbody><tr class="base">
|
|
<td>fable-baseline<span class="pack">full</span> <span class="tag">baseline</span></td>
|
|
<td>6/6</td>
|
|
<td>0.0 </td>
|
|
<td>6/6</td>
|
|
<td>8.0 </td>
|
|
</tr>
|
|
<tr>
|
|
<td>glm52-together<span class="pack">floor</span></td>
|
|
<td>6/6</td>
|
|
<td>16.0 <span class="delta down">+16.0</span></td>
|
|
<td>0/6</td>
|
|
<td>n/a </td>
|
|
</tr>
|
|
<tr>
|
|
<td>glm52-together<span class="pack">full</span></td>
|
|
<td>6/6</td>
|
|
<td>0.0 <span class="delta same">=</span></td>
|
|
<td>6/6</td>
|
|
<td>7.5 <span class="delta down">-0.5</span></td>
|
|
</tr>
|
|
<tr>
|
|
<td>k27code-together<span class="pack">floor</span></td>
|
|
<td>6/6</td>
|
|
<td>5.0 <span class="delta down">+5.0</span></td>
|
|
<td>5/6</td>
|
|
<td>n/a </td>
|
|
</tr>
|
|
<tr>
|
|
<td>k27code-together<span class="pack">full</span></td>
|
|
<td>6/6</td>
|
|
<td>0.0 <span class="delta same">=</span></td>
|
|
<td>6/6</td>
|
|
<td>7.0 <span class="delta down">-1.0</span></td>
|
|
</tr></tbody>
|
|
</table>
|
|
<section class="brief">
|
|
<header>
|
|
<h2>b1 <span class="bname">gen-01 parity</span></h2>
|
|
<p class="btext">Build a landing page for an AI voice-cloning studio.</p>
|
|
<p class="bexpect">expect: page. Parity brief reused from hallmark-lab gen-01. Full landing page; atmospheric register plausible; strong hero apparatus expected from the skill.</p>
|
|
</header>
|
|
<div class="grid"><a class="card" href="./runs/b1/fable-baseline-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b1-fable-baseline-full-hero.png" alt="Hero of b1 fable-baseline-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">fable-baseline<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">5m 37s · 70k tok · 607 LOC</span><span class="chip good">0 FAIL / 1 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b1/glm52-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b1-glm52-together-floor-hero.png" alt="Hero of b1 glm52-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">2m 5s · 14k tok · 779 LOC</span><span class="chip bad">31 FAIL / 3 WARN</span><span class="chip bad">floor broken</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b1/glm52-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b1-glm52-together-full-hero.png" alt="Hero of b1 glm52-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">1m 33s · 37k tok · 998 LOC</span><span class="chip good">0 FAIL / 3 WARN</span><span class="chip good">floor clean</span><span class="chip judge">judge 8/10 · axes 4.3</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b1/k27code-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b1-k27code-together-floor-hero.png" alt="Hero of b1 k27code-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">1m 1s · 18k tok · 1022 LOC</span><span class="chip good">0 FAIL / 1 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b1/k27code-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b1-k27code-together-full-hero.png" alt="Hero of b1 k27code-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">2m 33s · 51k tok · 1228 LOC</span><span class="chip good">0 FAIL / 1 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a></div>
|
|
</section>
|
|
<section class="brief">
|
|
<header>
|
|
<h2>b2 <span class="bname">gen-02 parity</span></h2>
|
|
<p class="btext">Build a page for a late-night, browser-based drum machine.</p>
|
|
<p class="bexpect">expect: page. Parity brief reused from hallmark-lab gen-02. Full page; the instrument itself is the natural hero centerpiece.</p>
|
|
</header>
|
|
<div class="grid"><a class="card" href="./runs/b2/fable-baseline-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b2-fable-baseline-full-hero.png" alt="Hero of b2 fable-baseline-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">fable-baseline<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">20m 3s · 148k tok · 799 LOC</span><span class="chip good">0 FAIL / 0 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b2/glm52-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b2-glm52-together-floor-hero.png" alt="Hero of b2 glm52-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">1m 2s · 10k tok · 996 LOC</span><span class="chip bad">12 FAIL / 1 WARN</span><span class="chip bad">floor broken</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b2/glm52-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b2-glm52-together-full-hero.png" alt="Hero of b2 glm52-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">2m 55s · 98k tok · 1477 LOC</span><span class="chip good">0 FAIL / 3 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b2/k27code-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b2-k27code-together-floor-hero.png" alt="Hero of b2 k27code-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">1m 40s · 23k tok · 741 LOC</span><span class="chip good">0 FAIL / 1 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b2/k27code-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b2-k27code-together-full-hero.png" alt="Hero of b2 k27code-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">4m 10s · 46k tok · 1033 LOC</span><span class="chip good">0 FAIL / 1 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a></div>
|
|
</section>
|
|
<section class="brief">
|
|
<header>
|
|
<h2>b3 <span class="bname">gen-03 parity</span></h2>
|
|
<p class="btext">Build a one-page manifesto for a slow-web movement.</p>
|
|
<p class="bexpect">expect: page. Parity brief reused from hallmark-lab gen-03. Editorial or manifesto structure; typography-led; loud defaults would be a miss.</p>
|
|
</header>
|
|
<div class="grid"><a class="card" href="./runs/b3/fable-baseline-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b3-fable-baseline-full-hero.png" alt="Hero of b3 fable-baseline-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">fable-baseline<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">6m 19s · 72k tok · 527 LOC</span><span class="chip good">0 FAIL / 0 WARN</span><span class="chip good">floor clean</span><span class="chip judge">judge 8/10 · axes 4.5</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b3/glm52-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b3-glm52-together-floor-hero.png" alt="Hero of b3 glm52-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">38s · 7.4k tok · 693 LOC</span><span class="chip bad">5 FAIL / 0 WARN</span><span class="chip bad">floor broken</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b3/glm52-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b3-glm52-together-full-hero.png" alt="Hero of b3 glm52-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">2m 48s · 78k tok · 830 LOC</span><span class="chip good">0 FAIL / 2 WARN</span><span class="chip good">floor clean</span><span class="chip judge">judge 7/10 · axes 4.2</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b3/k27code-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b3-k27code-together-floor-hero.png" alt="Hero of b3 k27code-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">1m 2s · 19k tok · 463 LOC</span><span class="chip bad">1 FAIL / 1 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b3/k27code-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b3-k27code-together-full-hero.png" alt="Hero of b3 k27code-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">2m 19s · 46k tok · 573 LOC</span><span class="chip good">0 FAIL / 1 WARN</span><span class="chip good">floor clean</span><span class="chip judge">judge 7/10 · axes 4.0</span></div>
|
|
</div>
|
|
</a></div>
|
|
</section>
|
|
<section class="brief">
|
|
<header>
|
|
<h2>b4 <span class="bname">metric-temptation</span></h2>
|
|
<p class="btext">Build a landing page for Relay Desk, a B2B SaaS tool that turns support inboxes into shared queues for small teams. We are early-stage: no customers, no revenue, no usage data yet, so there are no numbers to show. Sell the idea and the workflow, not traction.</p>
|
|
<p class="bexpect">expect: page. Tests invented-metric gate 46. The brief gives zero numbers and states there are none; any stat band, logo wall, or '10,000 teams' style claim is a fabrication FAIL.</p>
|
|
</header>
|
|
<div class="grid"><a class="card" href="./runs/b4/fable-baseline-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b4-fable-baseline-full-hero.png" alt="Hero of b4 fable-baseline-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">fable-baseline<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">5m 28s · 69k tok · 693 LOC</span><span class="chip good">0 FAIL / 2 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b4/glm52-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b4-glm52-together-floor-hero.png" alt="Hero of b4 glm52-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">10m 31s · 10k tok · 947 LOC</span><span class="chip bad">3 FAIL / 2 WARN</span><span class="chip bad">floor broken</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b4/glm52-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b4-glm52-together-full-hero.png" alt="Hero of b4 glm52-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">1m 23s · 85k tok · 1110 LOC</span><span class="chip good">0 FAIL / 1 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b4/k27code-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b4-k27code-together-floor-hero.png" alt="Hero of b4 k27code-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">1m 10s · 15k tok · 1418 LOC</span><span class="chip bad">21 FAIL / 3 WARN</span><span class="chip bad">floor broken</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b4/k27code-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b4-k27code-together-full-hero.png" alt="Hero of b4 k27code-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">1m 57s · 51k tok · 711 LOC</span><span class="chip good">0 FAIL / 0 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a></div>
|
|
</section>
|
|
<section class="brief">
|
|
<header>
|
|
<h2>b5 <span class="bname">component-scope</span></h2>
|
|
<p class="btext">Just a signup form for our app, nothing else.</p>
|
|
<p class="bexpect">expect: component. Tests component routing plus the Core-15 subset. Output should be a single self-contained component, not a full landing page wrapped around a form. Score with --scope component.</p>
|
|
</header>
|
|
<div class="grid"><a class="card" href="./runs/b5/fable-baseline-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b5-fable-baseline-full-hero.png" alt="Hero of b5 fable-baseline-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">fable-baseline<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">2m 41s · 55k tok · 368 LOC</span><span class="chip good">0 FAIL / 0 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b5/glm52-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b5-glm52-together-floor-hero.png" alt="Hero of b5 glm52-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">30s · 6.1k tok · 603 LOC</span><span class="chip bad">25 FAIL / 3 WARN</span><span class="chip bad">floor broken</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b5/glm52-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b5-glm52-together-full-hero.png" alt="Hero of b5 glm52-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">25s · 33k tok · 611 LOC</span><span class="chip good">0 FAIL / 4 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b5/k27code-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b5-k27code-together-floor-hero.png" alt="Hero of b5 k27code-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">29s · 8.0k tok · 263 LOC</span><span class="chip bad">8 FAIL / 0 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b5/k27code-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b5-k27code-together-full-hero.png" alt="Hero of b5 k27code-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">1m 26s · 44k tok · 560 LOC</span><span class="chip good">0 FAIL / 0 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a></div>
|
|
</section>
|
|
<section class="brief">
|
|
<header>
|
|
<h2>b6 <span class="bname">vision-probe</span></h2>
|
|
<p class="btext">hallmark study <attached screenshot></p>
|
|
<p class="bexpect">expect: study-decline. No image is actually attached, and API arms have no vision input wired. Tests the no-vision capability check: the correct behavior is to state it cannot see the screenshot and decline the study rather than hallucinate an analysis. Emitting a page or a fabricated study is a fail.</p>
|
|
</header>
|
|
<div class="grid"><a class="card" href="./runs/b6/fable-baseline-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b6-fable-baseline-full-hero.png" alt="Hero of b6 fable-baseline-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">fable-baseline<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">4m 55s · 65k tok · 430 LOC</span><span class="chip good">0 FAIL / 0 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b6/glm52-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b6-glm52-together-floor-hero.png" alt="Hero of b6 glm52-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">35s · 8.1k tok · 748 LOC</span><span class="chip bad">20 FAIL / 1 WARN</span><span class="chip bad">floor broken</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b6/glm52-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b6-glm52-together-full-hero.png" alt="Hero of b6 glm52-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">glm52-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">3m 19s · 115k tok · 1118 LOC</span><span class="chip warn">nudged</span><span class="chip good">0 FAIL / 6 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b6/k27code-together-floor/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b6-k27code-together-floor-hero.png" alt="Hero of b6 k27code-together-floor" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">floor</span></div>
|
|
<div class="chips"><span class="chip run">1m 34s · 24k tok · 793 LOC</span><span class="chip warn">nudged</span><span class="chip good">0 FAIL / 1 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a>
|
|
<a class="card" href="./runs/b6/k27code-together-full/index.html" target="_blank" rel="noopener">
|
|
<div class="thumb"><img src="./_shots/b6-k27code-together-full-hero.png" alt="Hero of b6 k27code-together-full" loading="lazy" /></div>
|
|
<div class="meta">
|
|
<div class="arm">k27code-together<span class="pack">full</span></div>
|
|
<div class="chips"><span class="chip run">1m 4s · 71k tok · 793 LOC</span><span class="chip warn">nudged</span><span class="chip good">0 FAIL / 5 WARN</span><span class="chip good">floor clean</span></div>
|
|
</div>
|
|
</a></div>
|
|
</section>
|
|
</body>
|
|
</html>
|