ginigen-ai's picture
Remove GINIGEN-AI badge
0678d23 verified
Raw
History Blame Contribute Delete
10.6 kB
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>RoboCasa Kitchen Leaderboard — GINIGEN-AI</title>
<style>
:root{--bg:#f7f9fc;--card:#ffffff;--bd:#e3e8f0;--fg:#1a2233;--mut:#64748b;--acc:#2563eb;--gold:#b45309;--grn:#059669;--head:#f1f5f9;}
*{box-sizing:border-box;}
body{margin:0;padding:36px 18px;background:var(--bg);color:var(--fg);
font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,sans-serif;line-height:1.6;}
.wrap{max-width:1020px;margin:0 auto;}
h1{font-size:32px;margin:0 0 6px;letter-spacing:-.5px;}
.sub{color:var(--mut);margin:0 0 16px;font-size:15px;}
.badges{display:flex;flex-wrap:wrap;gap:7px;margin:0 0 22px;}
.badges img{height:22px;}
.about{background:var(--card);border:1px solid var(--bd);border-radius:14px;padding:18px 20px;
margin:0 0 22px;box-shadow:0 1px 3px rgba(15,23,42,.05);}
.about h2{margin:0 0 10px;font-size:17px;}
.about p{margin:0 0 9px;font-size:14.5px;color:#334155;}
.about p:last-child{margin-bottom:0;}
.about b{color:var(--fg);}
.warn{background:#eff4ff;border:1px solid #d6e2ff;border-radius:12px;padding:12px 16px;
margin:0 0 26px;color:#3b4a66;font-size:13.5px;}
h2.sec{font-size:20px;margin:30px 0 10px;}
table{width:100%;border-collapse:collapse;background:var(--card);border:1px solid var(--bd);
border-radius:12px;overflow:hidden;font-size:14px;box-shadow:0 1px 3px rgba(15,23,42,.05);}
th,td{padding:11px 13px;text-align:left;border-bottom:1px solid var(--bd);}
th{background:var(--head);color:var(--mut);font-weight:600;font-size:11.5px;text-transform:uppercase;letter-spacing:.5px;}
tr:last-child td{border-bottom:none;}
tr.top td{background:#fffaf0;}
.rank{font-weight:800;color:var(--gold);}
.sr{font-weight:800;color:var(--grn);}
a{color:var(--acc);text-decoration:none;}
a:hover{text-decoration:underline;}
.foot{color:var(--mut);font-size:13px;margin-top:30px;border-top:1px solid var(--bd);padding-top:18px;}
form{background:var(--card);border:1px solid var(--bd);border-radius:14px;padding:20px 20px 10px;
margin-top:8px;box-shadow:0 1px 3px rgba(15,23,42,.05);}
.row{display:flex;gap:14px;flex-wrap:wrap;}
.fld{flex:1;min-width:185px;margin-bottom:14px;}
label{display:block;font-size:11.5px;color:var(--mut);margin-bottom:5px;text-transform:uppercase;letter-spacing:.4px;font-weight:600;}
input,select{width:100%;padding:10px 12px;background:#fff;border:1px solid #cbd5e1;border-radius:9px;color:var(--fg);font-size:14px;}
input:focus,select:focus{outline:none;border-color:var(--acc);box-shadow:0 0 0 3px rgba(37,99,235,.12);}
button{background:var(--acc);color:#fff;border:none;border-radius:9px;padding:11px 24px;font-size:14px;font-weight:600;cursor:pointer;margin-bottom:12px;}
button:hover{background:#1d4ed8;}
#msg{font-size:14px;margin:4px 0 12px;min-height:20px;}
</style>
</head>
<body>
<div class="wrap">
<h1>🍳 RoboCasa Kitchen Leaderboard</h1>
<p class="sub">A neutral, community-maintained leaderboard for Vision-Language-Action (VLA) policies — by <a href="https://huggingface.co/ginigen-ai">GINIGEN-AI</a></p>
<div class="badges">
<a href="https://robocasa.ai"><img alt="RoboCasa" src="https://img.shields.io/badge/Project-RoboCasa.ai-2563eb"></a>
<a href="https://arxiv.org/abs/2406.02523"><img alt="RoboCasa paper" src="https://img.shields.io/badge/RoboCasa-arXiv%202406.02523-b31b1b"></a>
<a href="https://arxiv.org/abs/2605.03269"><img alt="RLDX-1" src="https://img.shields.io/badge/RLDX--1%20SOTA-arXiv%202605.03269-b31b1b"></a>
<a href="https://arxiv.org/abs/2503.14734"><img alt="GR00T" src="https://img.shields.io/badge/GR00T%20N1-arXiv%202503.14734-b31b1b"></a>
<a href="https://arxiv.org/abs/2410.24164"><img alt="pi0" src="https://img.shields.io/badge/%CF%800-arXiv%202410.24164-b31b1b"></a>
<a href="https://github.com/huggingface/lerobot"><img alt="LeRobot" src="https://img.shields.io/badge/%F0%9F%A4%97-LeRobot-ffd21e"></a>
<img alt="license" src="https://img.shields.io/badge/license-MIT-059669">
</div>
<div class="about">
<h2>📖 What is this?</h2>
<p><b>RoboCasa Kitchen</b> is a robot-learning benchmark where a single-arm robot (Franka Panda) performs <b>24 atomic kitchen manipulation tasks</b> — picking objects, opening drawers/doors, turning faucets, pressing buttons, and more — inside a photorealistic simulator.</p>
<p>This board tracks the <b>average success rate</b> of <b>Vision-Language-Action (VLA)</b> policies: models that take <b>camera images + a natural-language instruction</b> as input and output <b>low-level robot actions</b>. It is the bridge between large multimodal models and real embodied control.</p>
<p>RoboCasa has <b>no official leaderboard</b>, and published numbers are scattered across papers under <b>different protocols</b>. GINIGEN-AI aggregates them <b>neutrally</b>, compares within a single <b>matched protocol</b> (the RLDX-1 Technical Report — the most recent head-to-head comparison), and <b>cites every source</b>.</p>
</div>
<div class="warn">⚠️ The main table uses the <b>matched protocol</b> from the RLDX-1 report. Entries measured under a different setup (other number of demos / authors' own eval) are listed <b>separately</b> and are <b>not directly comparable</b>. Spotted an error, or want to add your model? Use the submit form below or the Community tab.</div>
<h2 class="sec">🏆 Kitchen 24-task (matched protocol)</h2>
<table>
<thead><tr><th>#</th><th>Model</th><th>SR&nbsp;(%)</th><th>Org</th><th>Backbone/Arch</th><th>Paper</th><th>Date</th><th>Protocol</th></tr></thead>
<tbody>
<tr class="top"><td class="rank">1</td><td><b>RLDX-1</b></td><td class="sr">70.6</td><td>RLWRLD / KAIST (Jinwoo Shin)</td><td>MSAT</td><td><a href="https://arxiv.org/abs/2605.03269">arXiv:2605.03269</a></td><td>2026-05</td><td>matched (RLDX-1 report)</td></tr>
<tr><td>2</td><td>GR00T N1.6</td><td class="sr">66.2</td><td>NVIDIA</td><td>GR00T</td><td><a href="https://arxiv.org/abs/2503.14734">arXiv:2503.14734</a></td><td>2026</td><td>reproduced in RLDX-1</td></tr>
<tr><td>3</td><td>GR00T N1.5</td><td class="sr">65.7</td><td>NVIDIA</td><td>GR00T</td><td><a href="https://arxiv.org/abs/2503.14734">arXiv:2503.14734</a></td><td>2025</td><td>reproduced in RLDX-1</td></tr>
<tr><td>4</td><td>&pi;0-FAST</td><td class="sr">63.6</td><td>Physical Intelligence</td><td>&pi;0 (FAST tok.)</td><td>&mdash;</td><td>2025</td><td>reproduced in RLDX-1</td></tr>
<tr><td>5</td><td>&pi;0</td><td class="sr">62.5</td><td>Physical Intelligence</td><td>&pi;0 (flow)</td><td><a href="https://arxiv.org/abs/2410.24164">arXiv:2410.24164</a></td><td>2024</td><td>reproduced in RLDX-1</td></tr>
<tr><td>6</td><td>&pi;0.5</td><td class="sr">62.1</td><td>Physical Intelligence</td><td>&pi;0.5</td><td><a href="https://arxiv.org/abs/2504.16054">arXiv:2504.16054</a></td><td>2025</td><td>reproduced in RLDX-1</td></tr>
</tbody></table>
<h2 class="sec">➕ Other protocols (not directly comparable)</h2>
<table>
<thead><tr><th>Model</th><th>Reported&nbsp;SR&nbsp;(%)</th><th>Org</th><th>Backbone</th><th>Source</th><th>Why separate</th></tr></thead>
<tbody>
<tr><td>Cosmos-Policy (Predict2-2B)</td><td class="sr">67.1</td><td>NVIDIA</td><td>2B (video-FM finetune)</td><td><a href="https://huggingface.co/nvidia/Cosmos-Policy-RoboCasa-Predict2-2B">model card</a></td><td>50 demos, NVIDIA-own protocol</td></tr>
</tbody></table>
<h2 class="sec">🤖 GR1-Tabletop variant (separate suite)</h2>
<table>
<thead><tr><th>Model</th><th>GR1-Tabletop&nbsp;24-task&nbsp;SR&nbsp;(%)</th><th>Org</th><th>Source</th></tr></thead>
<tbody>
<tr><td>GR00T (h=16)</td><td class="sr">59.7</td><td>NVIDIA</td><td><a href="https://arxiv.org/abs/2604.05014">arXiv:2604.05014</a> (StarVLA)</td></tr>
<tr><td>TwinBrainVLA</td><td class="sr">54.6</td><td>&mdash;</td><td><a href="https://arxiv.org/abs/2601.14133">arXiv:2601.14133</a></td></tr>
<tr><td>VP-VLA</td><td class="sr">53.8</td><td>&mdash;</td><td><a href="https://arxiv.org/abs/2603.22003">arXiv:2603.22003</a></td></tr>
<tr><td>StarVLA-OFT</td><td class="sr">48.8</td><td>&mdash;</td><td><a href="https://arxiv.org/abs/2604.05014">arXiv:2604.05014</a></td></tr>
<tr><td>GR00T-N1.6</td><td class="sr">24.2</td><td>NVIDIA</td><td>RoboCasa-GR1 (no-collision 7.0%)</td></tr>
</tbody></table>
<h2 class="sec">📝 Submit your result</h2>
<p class="sub" style="margin:0 0 8px">Submissions are stored privately and reviewed before appearing on the board.</p>
<form id="sf">
<div class="row">
<div class="fld"><label>Model name *</label><input name="model" required placeholder="e.g. MyVLA-7B"></div>
<div class="fld"><label>Success rate % *</label><input name="sr" type="number" step="0.1" min="0" max="100" required placeholder="e.g. 64.3"></div>
</div>
<div class="row">
<div class="fld"><label>Protocol *</label><select name="protocol">
<option>Kitchen 24-task (matched)</option>
<option>Other protocol</option>
<option>GR1-Tabletop</option></select></div>
<div class="fld"><label>Paper / URL</label><input name="paper" placeholder="arXiv or HF link"></div>
<div class="fld"><label>Your name / org *</label><input name="submitter" required placeholder="e.g. GINIGEN-AI"></div>
</div>
<button type="submit">Submit</button>
<div id="msg"></div>
</form>
<div class="foot">
<b>References:</b>
<a href="https://arxiv.org/abs/2605.03269">RLDX-1</a> ·
<a href="https://arxiv.org/abs/2406.02523">RoboCasa</a> ·
<a href="https://arxiv.org/abs/2603.04356">RoboCasa365</a> ·
<a href="https://arxiv.org/abs/2503.14734">GR00T N1</a> ·
<a href="https://arxiv.org/abs/2410.24164">&pi;0</a> ·
<a href="https://github.com/huggingface/lerobot">LeRobot</a> ·
<a href="https://robocasa.ai">RoboCasa.ai</a><br>
Maintained by <a href="https://huggingface.co/ginigen-ai">GINIGEN-AI</a>. Not affiliated with the RoboCasa authors. Corrections welcome via the Community tab.
</div>
</div>
<script>
const sf = document.getElementById('sf'), msg = document.getElementById('msg');
sf.addEventListener('submit', async (e) => {
e.preventDefault();
msg.style.color = '#64748b'; msg.textContent = 'Submitting…';
try {
const r = await fetch('/submit', { method: 'POST', body: new FormData(sf) });
const j = await r.json();
if (j.ok) { msg.style.color = '#059669'; msg.textContent = '✅ Submitted — pending review. Thank you!'; sf.reset(); }
else { msg.style.color = '#dc2626'; msg.textContent = '❌ ' + (j.error || 'failed'); }
} catch (err) { msg.style.color = '#dc2626'; msg.textContent = '❌ network error'; }
});
</script>
</body>
</html>