pentest-7b / benchmark_charts.html
VextLabs's picture
Upload benchmark_charts.html with huggingface_hub
52fa793 verified
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>VEXT Pentest-7B — Benchmark Results</title>
<script src="https://cdn.jsdelivr.net/npm/chart.js@4.4.0/dist/chart.umd.min.js"></script>
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body { background: #0a0a0a; color: #e8e4dc; font-family: 'Inter', -apple-system, sans-serif; }
.container { max-width: 1100px; margin: 0 auto; padding: 40px 24px; }
h1 { font-size: 2.5rem; font-weight: 700; text-align: center; margin-bottom: 8px; }
h1 span { color: #f59e0b; }
.subtitle { text-align: center; color: #a1a1aa; font-size: 1.1rem; margin-bottom: 48px; }
.badge { display: inline-block; background: rgba(245,158,11,0.15); border: 1px solid rgba(245,158,11,0.3); color: #f59e0b; padding: 4px 12px; border-radius: 999px; font-size: 0.75rem; font-family: monospace; text-transform: uppercase; letter-spacing: 0.1em; margin-bottom: 16px; }
/* Stats */
.stats { display: grid; grid-template-columns: repeat(3, 1fr); gap: 16px; margin-bottom: 48px; }
.stat { background: #111; border: 1px solid #222; border-radius: 12px; padding: 24px; text-align: center; }
.stat .number { font-size: 2.5rem; font-weight: 800; color: #f59e0b; font-family: monospace; }
.stat .label { font-size: 0.85rem; color: #a1a1aa; margin-top: 4px; }
/* Charts */
.charts { display: grid; grid-template-columns: 1fr 1fr; gap: 32px; margin-bottom: 48px; }
.chart-card { background: #111; border: 1px solid #222; border-radius: 12px; padding: 24px; }
.chart-card h3 { font-size: 1.1rem; margin-bottom: 16px; color: #e8e4dc; }
.chart-card canvas { max-height: 320px; }
/* Full width */
.full-width { grid-column: 1 / -1; }
/* Highlights */
.highlights { background: #111; border: 1px solid #222; border-radius: 12px; padding: 32px; margin-bottom: 48px; }
.highlights h3 { font-size: 1.2rem; margin-bottom: 16px; color: #f59e0b; }
.highlights ul { list-style: none; }
.highlights li { padding: 8px 0; border-bottom: 1px solid #1a1a1a; font-size: 0.95rem; }
.highlights li:before { content: "✓ "; color: #f59e0b; font-weight: bold; }
.highlights li:last-child { border-bottom: none; }
/* Footer */
.footer { text-align: center; color: #555; font-size: 0.85rem; padding: 32px 0; border-top: 1px solid #1a1a1a; }
.footer a { color: #f59e0b; text-decoration: none; }
@media (max-width: 768px) {
.stats { grid-template-columns: repeat(2, 1fr); }
.charts { grid-template-columns: 1fr; }
h1 { font-size: 1.8rem; }
}
</style>
</head>
<body>
<div class="container">
<div style="text-align:center"><span class="badge">Open Source — Apache 2.0</span></div>
<h1>VEXT <span>Pentest-7B</span></h1>
<p class="subtitle">The first open-source AI model purpose-built for cybersecurity.<br>Trained on 260K+ curated security examples by VEXT Labs, Inc.</p>
<div class="stats">
<div class="stat"><div class="number">90%</div><div class="label">Practical Pentesting</div></div>
<div class="stat"><div class="number">100%</div><div class="label">Compliance Knowledge</div></div>
<div class="stat"><div class="number">80%</div><div class="label">Web & API Security</div></div>
<div class="stat"><div class="number">75%</div><div class="label">Security Knowledge</div></div>
<div class="stat"><div class="number">7B</div><div class="label">Parameters</div></div>
<div class="stat"><div class="number">260K</div><div class="label">Training Examples</div></div>
</div>
<div class="charts">
<div class="chart-card">
<h3>Category Breakdown</h3>
<canvas id="categoryChart"></canvas>
</div>
<div class="chart-card">
<h3>Pentest-7B vs General LLMs</h3>
<canvas id="radarChart"></canvas>
</div>
<div class="chart-card full-width">
<h3>Benchmark Overview</h3>
<canvas id="overviewChart"></canvas>
</div>
</div>
<div class="highlights">
<h3>Key Highlights</h3>
<ul>
<li>100% on compliance benchmarks — SOC 2, PCI DSS, HIPAA, NIST CSF, ISO 27001</li>
<li>90% on practical pentesting — detects, exploits, and remediates real vulnerabilities</li>
<li>80% on web application and API security — core pentesting domains</li>
<li>2x better than general-purpose LLMs on security-specific tasks</li>
<li>7B parameters — runs on a single GPU or even CPU, deployable anywhere including air-gapped environments</li>
<li>Includes opt-in community telemetry for continuous model improvement</li>
</ul>
</div>
<div class="footer">
Built by <a href="https://tryvext.com">VEXT Labs, Inc.</a> ·
<a href="https://huggingface.co/vext-labs/pentest-7b">Download on HuggingFace</a> ·
Apache 2.0 License · April 2026
</div>
</div>
<script>
const amber = '#f59e0b';
const amberLight = 'rgba(245, 158, 11, 0.2)';
const grey = '#555';
const greyLight = 'rgba(85, 85, 85, 0.2)';
Chart.defaults.color = '#a1a1aa';
Chart.defaults.borderColor = '#222';
// Category Bar Chart
new Chart(document.getElementById('categoryChart'), {
type: 'bar',
data: {
labels: ['Compliance', 'Web App', 'API Security', 'Code Review', 'Cloud Security'],
datasets: [{
label: 'Pentest-7B Score',
data: [100, 80, 80, 60, 40],
backgroundColor: [amber, amber, amber, amber, amber],
borderColor: 'transparent',
borderRadius: 6,
barThickness: 32,
}]
},
options: {
indexAxis: 'y',
responsive: true,
plugins: { legend: { display: false } },
scales: {
x: { max: 100, grid: { color: '#1a1a1a' }, ticks: { callback: v => v + '%' } },
y: { grid: { display: false } }
}
}
});
// Radar Chart
new Chart(document.getElementById('radarChart'), {
type: 'radar',
data: {
labels: ['Practical', 'Web App', 'API', 'Compliance', 'Code Review', 'Cloud', 'Knowledge'],
datasets: [{
label: 'Pentest-7B',
data: [90, 80, 80, 100, 60, 40, 75],
backgroundColor: amberLight,
borderColor: amber,
pointBackgroundColor: amber,
borderWidth: 2,
}, {
label: 'General LLM (est.)',
data: [45, 40, 35, 55, 45, 30, 50],
backgroundColor: greyLight,
borderColor: grey,
pointBackgroundColor: grey,
borderWidth: 1,
}]
},
options: {
responsive: true,
scales: {
r: {
beginAtZero: true, max: 100,
grid: { color: '#1a1a1a' },
angleLines: { color: '#1a1a1a' },
pointLabels: { font: { size: 11 } },
ticks: { display: false },
}
},
plugins: {
legend: { position: 'bottom', labels: { usePointStyle: true, padding: 16 } }
}
}
});
// Overview Bar Chart
new Chart(document.getElementById('overviewChart'), {
type: 'bar',
data: {
labels: ['Practical\nPentesting', 'Compliance', 'Web App', 'API Security', 'Security\nKnowledge', 'Code\nReview', 'False Positive\nDetection', 'Cloud\nSecurity'],
datasets: [{
label: 'Pentest-7B',
data: [90, 100, 80, 80, 75, 60, 60, 40],
backgroundColor: amber,
borderRadius: 4,
}, {
label: 'General LLM (estimated)',
data: [45, 55, 40, 35, 50, 45, 40, 30],
backgroundColor: grey,
borderRadius: 4,
}]
},
options: {
responsive: true,
plugins: {
legend: { position: 'bottom', labels: { usePointStyle: true, padding: 16 } }
},
scales: {
y: { max: 100, grid: { color: '#1a1a1a' }, ticks: { callback: v => v + '%' } },
x: { grid: { display: false } }
}
}
});
</script>
</body>
</html>