| <!DOCTYPE html> |
| <html lang="en"> |
| <head> |
| <meta charset="UTF-8"> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| <title>Tiny-ML Leaderboard</title> |
| <script src="https://cdn.jsdelivr.net/npm/chart.js@4"></script> |
| <style> |
| :root { |
| --bg: #0d1117; |
| --card: #161b22; |
| --border: #30363d; |
| --text: #c9d1d9; |
| --accent: #58a6ff; |
| --green: #3fb950; |
| --orange: #d29922; |
| --compactai: #3fb950; |
| --supralabs: #58a6ff; |
| } |
| * { margin: 0; padding: 0; box-sizing: border-box; } |
| body { font-family: -apple-system,BlinkMacSystemFont,'Segoe UI',Helvetica,Arial,sans-serif; background: var(--bg); color: var(--text); padding: 2rem; } |
| .container { max-width: 1200px; margin: 0 auto; } |
| h1 { font-size: 1.8rem; margin-bottom: .25rem; } |
| .subtitle { color: #8b949e; margin-bottom: 2rem; font-size: .95rem; } |
| .note { background: var(--card); border: 1px solid var(--border); border-radius: 8px; padding: 1rem; margin-bottom: 2rem; font-size: .9rem; line-height: 1.5; } |
| .note a { color: var(--accent); } |
| .section-title { font-size: 1.2rem; margin: 2rem 0 1rem; padding-bottom: .5rem; border-bottom: 1px solid var(--border); } |
| .chart-grid { display: grid; grid-template-columns: 1fr 1fr; gap: 1.5rem; margin-bottom: 2rem; } |
| .chart-card { background: var(--card); border: 1px solid var(--border); border-radius: 8px; padding: 1rem; } |
| .chart-card.full { grid-column: 1 / -1; } |
| .chart-card h3 { font-size: .95rem; margin-bottom: .75rem; color: var(--text); } |
| .chart-card canvas { max-height: 360px; } |
| .legend { display: flex; gap: 1.5rem; margin-bottom: .75rem; font-size: .8rem; } |
| .legend-item { display: flex; align-items: center; gap: .4rem; } |
| .legend-dot { width: 10px; height: 10px; border-radius: 50%; } |
| table { width: 100%; border-collapse: collapse; font-size: .85rem; } |
| th { background: var(--card); padding: .75rem .5rem; text-align: center; border: 1px solid var(--border); font-weight: 600; white-space: nowrap; } |
| td { padding: .6rem .5rem; text-align: center; border: 1px solid var(--border); } |
| td:first-child, th:first-child { text-align: left; padding-left: 1rem; } |
| tr:hover td { background: rgba(88,166,255,.05); } |
| .org-tag { display: inline-block; padding: .15rem .5rem; border-radius: 4px; font-size: .75rem; font-weight: 600; } |
| .org-compactai { background: #3fb95033; color: var(--compactai); } |
| .org-supralabs { background: #1f6feb33; color: var(--supralabs); } |
| .row-compactai { border-left: 3px solid var(--compactai); } |
| .row-supralabs { border-left: 3px solid var(--supralabs); } |
| .best { color: var(--green); font-weight: 700; } |
| .na { color: #484f58; font-style: italic; } |
| .links a { color: var(--accent); text-decoration: none; } |
| .links a:hover { text-decoration: underline; } |
| footer { margin-top: 3rem; padding-top: 1.5rem; border-top: 1px solid var(--border); font-size: .8rem; color: #484f58; text-align: center; } |
| footer a { color: var(--accent); } |
| .methodology { margin-top: 2rem; } |
| .methodology h3 { margin-bottom: .5rem; } |
| .methodology p { font-size: .85rem; line-height: 1.6; color: #8b949e; } |
| @media (max-width: 768px) { |
| body { padding: 1rem; } |
| .chart-grid { grid-template-columns: 1fr; } |
| table { font-size: .75rem; } |
| th, td { padding: .4rem .3rem; } |
| } |
| </style> |
| </head> |
| <body> |
| <div class="container"> |
|
|
| <h1>Tiny-ML Leaderboard</h1> |
| <p class="subtitle">Sub-100M parameter language models, same eval harness, transparent methodology.</p> |
|
|
| <div class="note"> |
| <strong>Why this exists.</strong> The community deserves a single place to compare tiny LMs fairly. |
| We include every model with verifiable benchmarks — ours, our competitors', yours. |
| <a href="https://huggingface.co/spaces/CompactAI-O/Tiny-ML-Leaderboard/discussions" target="_blank">Submit a model via PR.</a><br> |
| </div> |
|
|
| <h2 class="section-title">Detailed Results</h2> |
|
|
| <table> |
| <thead> |
| <tr> |
| <th>Model</th> |
| <th>Org</th> |
| <th>Params</th> |
| <th>WikiText-2 ↓</th> |
| <th>BLiMP ↑</th> |
| <th>ARC-Easy ↑</th> |
| <th>Training Tokens</th> |
| <th>Links</th> |
| </tr> |
| </thead> |
| <tbody> |
|
|
| <tr class="row-supralabs"> |
| <td><strong>Supra-50M-Instruct</strong></td> |
| <td><span class="org-tag org-supralabs">SupraLabs</span></td> |
| <td>51.8M</td> |
| <td class="na">not reported</td> |
| <td><span class="best">76.3%</span></td> |
| <td><span class="best">52.2%</span></td> |
| <td>20B</td> |
| <td class="links"><a href="https://huggingface.co/SupraLabs/Supra-50M-Instruct">card</a> <a href="https://huggingface.co/SupraLabs/Supra-50M-Base">base</a></td> |
| </tr> |
| <tr class="row-compactai"> |
| <td><strong>Glint-1.3 (merged)</strong></td> |
| <td><span class="org-tag org-compactai">CompactAI</span></td> |
| <td>982K</td> |
| <td>3.08</td> |
| <td>68.7%</td> |
| <td>32.5%</td> |
| <td>100B</td> |
| <td class="links"><a href="https://huggingface.co/CompactAI-O/Glint-1.3">card</a></td> |
| </tr> |
| <tr class="row-supralabs"> |
| <td><strong>Supra-Mini-v5</strong></td> |
| <td><span class="org-tag org-supralabs">SupraLabs</span></td> |
| <td>7.87M</td> |
| <td><span class="best">2.66</span></td> |
| <td>63.5%</td> |
| <td>34.4%</td> |
| <td class="na">—</td> |
| <td class="links"><a href="https://huggingface.co/SupraLabs/Supra-Mini-v5-8M">card</a></td> |
| </tr> |
| <tr class="row-compactai"> |
| <td><strong>Glint-1</strong></td> |
| <td><span class="org-tag org-compactai">CompactAI</span></td> |
| <td>1M</td> |
| <td>4.07</td> |
| <td>61.2%</td> |
| <td>32.0%</td> |
| <td>100B</td> |
| <td class="links"><a href="https://huggingface.co/CompactAI-O/Glint-1">card</a></td> |
| </tr> |
| <tr class="row-supralabs"> |
| <td><strong>Supra-Mini-v4</strong></td> |
| <td><span class="org-tag org-supralabs">SupraLabs</span></td> |
| <td>2.62M</td> |
| <td>3.17</td> |
| <td>60.7%</td> |
| <td>31.5%</td> |
| <td class="na">—</td> |
| <td class="links"><a href="https://huggingface.co/SupraLabs/Supra-Mini-v4-2M">card</a></td> |
| </tr> |
| <tr class="row-compactai"> |
| <td><strong>Glint-0.4</strong></td> |
| <td><span class="org-tag org-compactai">CompactAI</span></td> |
| <td>1M</td> |
| <td>5.24</td> |
| <td>58.5%</td> |
| <td>31.0%</td> |
| <td>10B</td> |
| <td class="links"><a href="https://huggingface.co/CompactAI-O/Glint-0.4">card</a></td> |
| </tr> |
| <tr class="row-supralabs"> |
| <td><strong>Supra-Mini-v3</strong></td> |
| <td><span class="org-tag org-supralabs">SupraLabs</span></td> |
| <td>468K</td> |
| <td>4.49</td> |
| <td>55.3%</td> |
| <td>27.3%</td> |
| <td class="na">—</td> |
| <td class="links"><a href="https://huggingface.co/SupraLabs/Supra-Mini-v3-0.5M">card</a></td> |
| </tr> |
| <tr class="row-supralabs"> |
| <td><strong>Supra-Mini-v2</strong></td> |
| <td><span class="org-tag org-supralabs">SupraLabs</span></td> |
| <td>168K</td> |
| <td>7.79</td> |
| <td>53.5%</td> |
| <td>26.8%</td> |
| <td class="na">—</td> |
| <td class="links"><a href="https://huggingface.co/SupraLabs/Supra-Mini-v2-0.1M">card</a></td> |
| </tr> |
| <tr class="row-compactai"> |
| <td><strong>Glint-0.2</strong></td> |
| <td><span class="org-tag org-compactai">CompactAI</span></td> |
| <td>1M</td> |
| <td class="na">TBD</td> |
| <td>49.8%</td> |
| <td>27.0%</td> |
| <td>~100M</td> |
| <td class="links"><a href="https://huggingface.co/CompactAI-O/Glint-0.2">card</a></td> |
| </tr> |
| <tr class="row-compactai"> |
| <td><strong>Glint-0.3</strong></td> |
| <td><span class="org-tag org-compactai">CompactAI</span></td> |
| <td>1M</td> |
| <td class="na">TBD</td> |
| <td>47.3%</td> |
| <td>25.5%</td> |
| <td>~100M</td> |
| <td class="links"><a href="https://huggingface.co/CompactAI-O/Glint-0.3">card</a></td> |
| </tr> |
| <tr class="row-compactai"> |
| <td><strong>Glint-0.1</strong></td> |
| <td><span class="org-tag org-compactai">CompactAI</span></td> |
| <td>1M</td> |
| <td class="na">TBD</td> |
| <td>46.7%</td> |
| <td>21.0%</td> |
| <td>~100M</td> |
| <td class="links"><a href="https://huggingface.co/CompactAI-O/Glint-0.1">card</a></td> |
| </tr> |
| <tr class="row-compactai"> |
| <td><strong>Shard-1</strong></td> |
| <td><span class="org-tag org-compactai">CompactAI</span></td> |
| <td>54.5M</td> |
| <td class="na">TBD</td> |
| <td class="na">TBD</td> |
| <td class="na">TBD</td> |
| <td>~20B</td> |
| <td class="links"><a href="https://huggingface.co/CompactAI-O/Shard-1">card</a></td> |
| </tr> |
| <tr class="row-supralabs"> |
| <td><strong>StorySupra-10M</strong></td> |
| <td><span class="org-tag org-supralabs">SupraLabs</span></td> |
| <td>12.6M</td> |
| <td class="na">not reported</td> |
| <td class="na">not reported</td> |
| <td class="na">not reported</td> |
| <td class="na">—</td> |
| <td class="links"><a href="https://huggingface.co/SupraLabs/StorySupra-10M">card</a></td> |
| </tr> |
| <tr class="row-supralabs"> |
| <td><strong>DistillSupra-0.2M</strong></td> |
| <td><span class="org-tag org-supralabs">SupraLabs</span></td> |
| <td>289K</td> |
| <td class="na">not reported</td> |
| <td class="na">not reported</td> |
| <td class="na">not reported</td> |
| <td class="na">—</td> |
| <td class="links"><a href="https://huggingface.co/SupraLabs/DistillSupra-0.2M">card</a></td> |
| </tr> |
| <tr class="row-supralabs"> |
| <td><strong>MicroSupra-1k</strong></td> |
| <td><span class="org-tag org-supralabs">SupraLabs</span></td> |
| <td>1K</td> |
| <td class="na">not reported</td> |
| <td class="na">not reported</td> |
| <td class="na">not reported</td> |
| <td class="na">—</td> |
| <td class="links"><a href="https://huggingface.co/SupraLabs/MicroSupra-1k">card</a></td> |
| </tr> |
| <tr class="row-compactai"> |
| <td><strong>TrueMath</strong></td> |
| <td><span class="org-tag org-compactai">CompactAI</span></td> |
| <td>1-layer</td> |
| <td class="na">—</td> |
| <td class="na">—</td> |
| <td class="na">—</td> |
| <td>synthetic</td> |
| <td class="links"><a href="https://huggingface.co/CompactAI-O/TrueMath">card</a></td> |
| </tr> |
|
|
| </tbody> |
| </table> |
|
|
| <h2 class="section-title">Benchmark Overview</h2> |
|
|
| <div class="legend"> |
| <span class="legend-item"><span class="legend-dot" style="background:var(--compactai)"></span> CompactAI</span> |
| <span class="legend-item"><span class="legend-dot" style="background:var(--supralabs)"></span> SupraLabs</span> |
| </div> |
|
|
| <div class="chart-grid"> |
| <div class="chart-card"> |
| <h3>BLiMP ↑ (higher is better)</h3> |
| <canvas id="blimpChart"></canvas> |
| </div> |
| <div class="chart-card"> |
| <h3>ARC-Easy ↑ (higher is better)</h3> |
| <canvas id="arcChart"></canvas> |
| </div> |
| <div class="chart-card full"> |
| <h3>WikiText-2 ↓ (lower is better)</h3> |
| <canvas id="wikiChart"></canvas> |
| </div> |
| </div> |
|
|
|
|
|
|
| <div class="methodology" style="margin-top:1.5rem"> |
| <h3>Add your model</h3> |
| <p> |
| Open a PR on this Space with your model's benchmark results and reproduction steps. |
| We require: params, training data provenance, eval harness used, and scores for at least 2 of the 3 benchmarks. |
| </p> |
| </div> |
|
|
| <footer> |
| <p>Tiny-ML Leaderboard by <a href="https://huggingface.co/CompactAI-O">CompactAI</a>. |
| Not affiliated with SupraLabs or LH-Tech-AI. |
| All benchmark data is self-reported by model authors unless otherwise noted.</p> |
| </footer> |
|
|
| </div> |
| <script> |
| const models = [ |
| { name: 'Supra-50M-Instruct', org: 'supralabs', blimp: 76.3, arc: 52.2, wiki: null }, |
| { name: 'Glint-1.3 (merged)', org: 'compactai', blimp: 68.7, arc: 32.5, wiki: 3.08 }, |
| { name: 'Supra-Mini-v5', org: 'supralabs', blimp: 63.5, arc: 34.4, wiki: 2.66 }, |
| { name: 'Glint-1', org: 'compactai', blimp: 61.2, arc: 32.0, wiki: 4.07 }, |
| { name: 'Supra-Mini-v4', org: 'supralabs', blimp: 60.7, arc: 31.5, wiki: 3.17 }, |
| { name: 'Glint-0.4', org: 'compactai', blimp: 58.5, arc: 31.0, wiki: 5.24 }, |
| { name: 'Supra-Mini-v3', org: 'supralabs', blimp: 55.3, arc: 27.3, wiki: 4.49 }, |
| { name: 'Supra-Mini-v2', org: 'supralabs', blimp: 53.5, arc: 26.8, wiki: 7.79 }, |
| { name: 'Glint-0.2', org: 'compactai', blimp: 49.8, arc: 27.0, wiki: null }, |
| { name: 'Glint-0.3', org: 'compactai', blimp: 47.3, arc: 25.5, wiki: null }, |
| { name: 'Glint-0.1', org: 'compactai', blimp: 46.7, arc: 21.0, wiki: null }, |
| ]; |
| |
| const colorMap = { compactai: '#3fb950', supralabs: '#58a6ff' }; |
| const bgMap = { compactai: 'rgba(63,185,80,0.7)', supralabs: 'rgba(88,166,255,0.7)' }; |
| |
| function buildChart(canvasId, metric, label, reverse) { |
| const m = metric === 'wiki' ? 'wiki' : metric; |
| const fmt = metric === 'wiki' ? v => v.toFixed(2) : v => v.toFixed(1) + '%'; |
| const sorted = models |
| .filter(d => d[metric] !== null) |
| .sort((a, b) => reverse ? a[metric] - b[metric] : b[metric] - a[metric]); |
| |
| new Chart(document.getElementById(canvasId), { |
| type: 'bar', |
| data: { |
| labels: sorted.map(d => d.name), |
| datasets: [{ |
| data: sorted.map(d => d[metric]), |
| backgroundColor: sorted.map(d => bgMap[d.org]), |
| borderColor: sorted.map(d => colorMap[d.org]), |
| borderWidth: 1, |
| borderRadius: 3, |
| }] |
| }, |
| options: { |
| indexAxis: 'y', |
| responsive: true, |
| maintainAspectRatio: true, |
| plugins: { |
| legend: { display: false }, |
| tooltip: { |
| callbacks: { |
| label: ctx => fmt(ctx.parsed.x) |
| } |
| } |
| }, |
| scales: { |
| x: { |
| beginAtZero: true, |
| grid: { color: 'rgba(255,255,255,0.06)' }, |
| ticks: { color: '#8b949e', callback: v => metric === 'wiki' ? v.toFixed(1) : v + '%' } |
| }, |
| y: { |
| grid: { display: false }, |
| ticks: { |
| color: '#c9d1d9', |
| font: { size: 11 }, |
| autoSkip: false, |
| callback: label => label.length > 18 ? label.slice(0, 17) + '…' : label |
| } |
| } |
| } |
| } |
| }); |
| } |
| |
| |
| function applyTableGradient() { |
| |
| const blimpMin = 46.7, blimpMax = 76.3; |
| const arcMin = 21.0, arcMax = 52.2; |
| const wikiMin = 2.66, wikiMax = 7.79; |
| |
| |
| const worstGreen = [255, 255, 255]; |
| const bestGreen = [63, 185, 80]; |
| |
| function getColor(value, min, max, lowerIsBetter) { |
| if (value === null || isNaN(value)) return ''; |
| let percent = (value - min) / (max - min); |
| |
| if (lowerIsBetter) percent = 1 - percent; |
| const clamped = Math.max(0, Math.min(1, percent)); |
| |
| |
| const adjusted = Math.pow(clamped, 2.5); |
| const r = Math.round(worstGreen[0] + (bestGreen[0] - worstGreen[0]) * adjusted); |
| const g = Math.round(worstGreen[1] + (bestGreen[1] - worstGreen[1]) * adjusted); |
| const b = Math.round(worstGreen[2] + (bestGreen[2] - worstGreen[2]) * adjusted); |
| return `rgb(${r}, ${g}, ${b})`; |
| } |
| |
| |
| const blimpCells = document.querySelectorAll('td:nth-child(5)'); |
| const arcCells = document.querySelectorAll('td:nth-child(6)'); |
| const wikiCells = document.querySelectorAll('td:nth-child(4)'); |
| |
| blimpCells.forEach(cell => { |
| const text = cell.textContent.replace('%', '').trim(); |
| if (text && text !== 'not reported' && text !== 'TBD' && text !== '—') { |
| const value = parseFloat(text); |
| if (!isNaN(value)) { |
| cell.style.color = getColor(value, blimpMin, blimpMax, false); |
| } |
| } |
| }); |
| |
| arcCells.forEach(cell => { |
| const text = cell.textContent.replace('%', '').trim(); |
| if (text && text !== 'not reported' && text !== 'TBD' && text !== '—') { |
| const value = parseFloat(text); |
| if (!isNaN(value)) { |
| cell.style.color = getColor(value, arcMin, arcMax, false); |
| } |
| } |
| }); |
| |
| wikiCells.forEach(cell => { |
| const text = cell.textContent.trim(); |
| if (text && text !== 'not reported' && text !== 'TBD' && text !== '—') { |
| const value = parseFloat(text); |
| if (!isNaN(value)) { |
| cell.style.color = getColor(value, wikiMin, wikiMax, true); |
| } |
| } |
| }); |
| } |
| |
| |
| window.addEventListener('DOMContentLoaded', applyTableGradient); |
| buildChart('blimpChart', 'blimp', 'BLiMP Accuracy', false); |
| buildChart('arcChart', 'arc', 'ARC-Easy Accuracy', false); |
| buildChart('wikiChart', 'wiki', 'WikiText-2 Perplexity', true); |
| </script> |
| </body> |
| </html> |
|
|
