|
|
<!DOCTYPE html> |
|
|
<html lang="en"> |
|
|
<head> |
|
|
<meta charset="UTF-8"> |
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"> |
|
|
<title>LLM4Law - Legal LLM Benchmarks</title> |
|
|
<script src="https://cdn.tailwindcss.com"></script> |
|
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css"> |
|
|
<script> |
|
|
tailwind.config = { |
|
|
theme: { |
|
|
extend: { |
|
|
colors: { |
|
|
'legal-blue': '#1a365d', |
|
|
'legal-gold': '#d4af37', |
|
|
} |
|
|
} |
|
|
} |
|
|
} |
|
|
</script> |
|
|
<style> |
|
|
.gradient-bg { |
|
|
background: linear-gradient(135deg, #1a365d 0%, #2c5282 100%); |
|
|
} |
|
|
.table-row-hover:hover { |
|
|
background-color: #f7fafc; |
|
|
transform: translateY(-2px); |
|
|
box-shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.1); |
|
|
} |
|
|
.scrollbar-hide::-webkit-scrollbar { |
|
|
display: none; |
|
|
} |
|
|
</style> |
|
|
</head> |
|
|
<body class="bg-gray-50 font-sans"> |
|
|
|
|
|
<header class="gradient-bg text-white shadow-lg"> |
|
|
<div class="container mx-auto px-4 py-6"> |
|
|
<div class="flex flex-col md:flex-row justify-between items-center"> |
|
|
<div class="flex items-center mb-4 md:mb-0"> |
|
|
<i class="fas fa-balance-scale text-3xl mr-3 text-legal-gold"></i> |
|
|
<div> |
|
|
<h1 class="text-2xl font-bold">LLM4Law</h1> |
|
|
<p class="text-sm opacity-80">Legal LLM Benchmarking</p> |
|
|
</div> |
|
|
</div> |
|
|
<nav class="flex space-x-6"> |
|
|
<a href="#" class="hover:text-legal-gold transition">Home</a> |
|
|
<a href="#" class="hover:text-legal-gold transition">Benchmarks</a> |
|
|
<a href="#" class="hover:text-legal-gold transition">Methodology</a> |
|
|
<a href="#" class="hover:text-legal-gold transition">About</a> |
|
|
</nav> |
|
|
</div> |
|
|
</div> |
|
|
</header> |
|
|
|
|
|
|
|
|
<section class="gradient-bg text-white py-16"> |
|
|
<div class="container mx-auto px-4 text-center"> |
|
|
<h2 class="text-3xl md:text-4xl font-bold mb-4">Legal LLM Benchmarking</h2> |
|
|
<p class="text-xl max-w-3xl mx-auto mb-8"> |
|
|
Quantitative analysis of local LLMs performance on legal tasks |
|
|
</p> |
|
|
<div class="flex flex-col md:flex-row justify-center gap-4"> |
|
|
<button class="bg-legal-gold hover:bg-yellow-600 text-legal-blue font-bold py-3 px-6 rounded-lg transition"> |
|
|
View Latest Results |
|
|
</button> |
|
|
<button class="border border-legal-gold hover:bg-white hover:bg-opacity-10 text-white font-bold py-3 px-6 rounded-lg transition"> |
|
|
Learn About Methodology |
|
|
</button> |
|
|
</div> |
|
|
</div> |
|
|
</section> |
|
|
|
|
|
|
|
|
<main class="container mx-auto px-4 py-12"> |
|
|
|
|
|
<section class="mb-16"> |
|
|
<div class="flex justify-between items-center mb-8"> |
|
|
<h2 class="text-2xl font-bold text-legal-blue">Legal Task Benchmarks</h2> |
|
|
<div class="flex items-center space-x-4"> |
|
|
<div class="relative"> |
|
|
<select class="appearance-none bg-white border border-gray-300 rounded-lg pl-4 pr-10 py-2 focus:outline-none focus:ring-2 focus:ring-legal-blue"> |
|
|
<option>All Models</option> |
|
|
<option>Llama 2</option> |
|
|
<option>Mistral</option> |
|
|
<option>GPT4All</option> |
|
|
</select> |
|
|
<i class="fas fa-chevron-down absolute right-3 top-3 text-gray-500"></i> |
|
|
</div> |
|
|
<button class="bg-legal-blue hover:bg-blue-900 text-white px-4 py-2 rounded-lg transition"> |
|
|
<i class="fas fa-download mr-2"></i> Export Data |
|
|
</button> |
|
|
</div> |
|
|
</div> |
|
|
|
|
|
<div class="bg-white rounded-xl shadow-md overflow-hidden"> |
|
|
<div class="overflow-x-auto scrollbar-hide"> |
|
|
<table class="min-w-full divide-y divide-gray-200"> |
|
|
<thead class="bg-gray-50"> |
|
|
<tr> |
|
|
<th scope="col" class="px-6 py-3 text-left text-xs font-medium text-gray-500 uppercase tracking-wider"> |
|
|
Model |
|
|
</th> |
|
|
<th scope="col" class="px-6 py-3 text-left text-xs font-medium text-gray-500 uppercase tracking-wider"> |
|
|
Version |
|
|
</th> |
|
|
<th scope="col" class="px-6 py-3 text-left text-xs font-medium text-gray-500 uppercase tracking-wider"> |
|
|
Contract Analysis |
|
|
</th> |
|
|
<th scope="col" class="px-6 py-3 text-left text-xs font-medium text-gray-500 uppercase tracking-wider"> |
|
|
Case Prediction |
|
|
</th> |
|
|
<th scope="col" class="px-6 py-3 text-left text-xs font-medium text-gray-500 uppercase tracking-wider"> |
|
|
Legal Research |
|
|
</th> |
|
|
<th scope="col" class="px-6 py-3 text-left text-xs font-medium text-gray-500 uppercase tracking-wider"> |
|
|
Document Drafting |
|
|
</th> |
|
|
<th scope="col" class="px-6 py-3 text-left text-xs font-medium text-gray-500 uppercase tracking-wider"> |
|
|
Overall |
|
|
</th> |
|
|
</tr> |
|
|
</thead> |
|
|
<tbody class="bg-white divide-y divide-gray-200"> |
|
|
|
|
|
<tr class="table-row-hover transition cursor-pointer"> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="flex-shrink-0 h-10 w-10 bg-blue-100 rounded-full flex items-center justify-center"> |
|
|
<i class="fas fa-robot text-blue-600"></i> |
|
|
</div> |
|
|
<div class="ml-4"> |
|
|
<div class="text-sm font-medium text-gray-900">Llama 2</div> |
|
|
<div class="text-sm text-gray-500">Meta</div> |
|
|
</div> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap text-sm text-gray-500"> |
|
|
7B-chat |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-green-500 h-2.5 rounded-full" style="width: 78%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">78%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-yellow-500 h-2.5 rounded-full" style="width: 65%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">65%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-red-500 h-2.5 rounded-full" style="width: 52%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">52%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-green-500 h-2.5 rounded-full" style="width: 82%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">82%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap text-sm font-bold text-legal-blue"> |
|
|
72% |
|
|
</td> |
|
|
</tr> |
|
|
|
|
|
|
|
|
<tr class="table-row-hover transition cursor-pointer"> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="flex-shrink-0 h-10 w-10 bg-purple-100 rounded-full flex items-center justify-center"> |
|
|
<i class="fas fa-cloud text-purple-600"></i> |
|
|
</div> |
|
|
<div class="ml-4"> |
|
|
<div class="text-sm font-medium text-gray-900">Mistral</div> |
|
|
<div class="text-sm text-gray-500">Mistral AI</div> |
|
|
</div> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap text-sm text-gray-500"> |
|
|
7B-v0.1 |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-green-500 h-2.5 rounded-full" style="width: 85%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">85%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-green-500 h-2.5 rounded-full" style="width: 78%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">78%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-yellow-500 h-2.5 rounded-full" style="width: 68%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">68%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-green-500 h-2.5 rounded-full" style="width: 88%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">88%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap text-sm font-bold text-legal-blue"> |
|
|
80% |
|
|
</td> |
|
|
</tr> |
|
|
|
|
|
<tr class="table-row-hover transition cursor-pointer"> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="flex-shrink-0 h-10 w-10 bg-green-100 rounded-full flex items-center justify-center"> |
|
|
<i class="fas fa-laptop-code text-green-600"></i> |
|
|
</div> |
|
|
<div class="ml-4"> |
|
|
<div class="text-sm font-medium text-gray-900">GPT4All</div> |
|
|
<div class="text-sm text-gray-500">Nomic AI</div> |
|
|
</div> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap text-sm text-gray-500"> |
|
|
Falcon-7B |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-yellow-500 h-2.5 rounded-full" style="width: 72%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">72%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-yellow-500 h-2.5 rounded-full" style="width: 70%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">70%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-red-500 h-2.5 rounded-full" style="width: 58%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">58%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap"> |
|
|
<div class="flex items-center"> |
|
|
<div class="w-24 bg-gray-200 rounded-full h-2.5"> |
|
|
<div class="bg-green-500 h-2.5 rounded-full" style="width: 80%"></div> |
|
|
</div> |
|
|
<span class="ml-2 text-sm font-medium text-gray-700">80%</span> |
|
|
</div> |
|
|
</td> |
|
|
<td class="px-6 py-4 whitespace-nowrap text-sm font-bold text-legal-blue"> |
|
|
70% |
|
|
</td> |
|
|
</tr> |
|
|
</tbody> |
|
|
</table> |
|
|
</div> |
|
|
</div> |
|
|
</section> |
|
|
|
|
|
|
|
|
<section class="mb-16"> |
|
|
<h2 class="text-2xl font-bold text-legal-blue mb-6">Benchmark Methodology</h2> |
|
|
<div class="grid md:grid-cols-3 gap-8"> |
|
|
<div class="bg-white p-6 rounded-xl shadow-md"> |
|
|
<div class="bg-blue-100 w-12 h-12 rounded-full flex items-center justify-center mb-4"> |
|
|
<i class="fas fa-clipboard-check text-blue-600 text-xl"></i> |
|
|
</div> |
|
|
<h3 class="text-lg font-semibold mb-2">Task Selection</h3> |
|
|
<p class="text-gray-600"> |
|
|
Carefully curated legal tasks representing real-world scenarios including contract analysis, case prediction, legal research, and document drafting. |
|
|
</p> |
|
|
</div> |
|
|
<div class="bg-white p-6 rounded-xl shadow-md"> |
|
|
<div class="bg-purple-100 w-12 h-12 rounded-full flex items-center justify-center mb-4"> |
|
|
<i class="fas fa-tasks text-purple-600 text-xl"></i> |
|
|
</div> |
|
|
<h3 class="text-lg font-semibold mb-2">Evaluation Criteria</h3> |
|
|
<p class="text-gray-600"> |
|
|
Each task is evaluated on accuracy, legal reasoning, citation quality, and practical applicability by a panel of IP attorneys. |
|
|
</p> |
|
|
</div> |
|
|
<div class="bg-white p-6 rounded-xl shadow-md"> |
|
|
<div class="bg-green-100 w-12 h-12 rounded-full flex items-center justify-center mb-4"> |
|
|
<i class="fas fa-server text-green-600 text-xl"></i> |
|
|
</div> |
|
|
<h3 class="text-lg font-semibold mb-2">Testing Environment</h3> |
|
|
<p class="text-gray-600"> |
|
|
All models tested on identical hardware (RTX 4090, 64GB RAM) with standardized prompts and temperature settings for fair comparison. |
|
|
</p> |
|
|
</div> |
|
|
</div> |
|
|
</section> |
|
|
|
|
|
|
|
|
<section> |
|
|
<h2 class="text-2xl font-bold text-legal-blue mb-6">Latest Updates</h2> |
|
|
<div class="bg-white rounded-xl shadow-md overflow-hidden"> |
|
|
<div class="p-6"> |
|
|
<div class="flex items-start mb-6 pb-6 border-b border-gray-100"> |
|
|
<div class="bg-legal-blue text-white rounded-lg p-3 mr-4"> |
|
|
<i class="fas fa-bullhorn text-xl"></i> |
|
|
</div> |
|
|
<div> |
|
|
<h3 class="font-semibold mb-1">New Benchmark: Mistral 7B vs. Llama 2 7B</h3> |
|
|
<p class="text-gray-600 mb-2">Added comprehensive comparison between the two leading 7B parameter models on contract analysis tasks.</p> |
|
|
<span class="text-sm text-gray-500">Posted: June 15, 2023</span> |
|
|
</div> |
|
|
</div> |
|
|
<div class="flex items-start"> |
|
|
<div class="bg-legal-gold text-legal-blue rounded-lg p-3 mr-4"> |
|
|
<i class="fas fa-chart-line text-xl"></i> |
|
|
</div> |
|
|
<div> |
|
|
<h3 class="font-semibold mb-1">Methodology Update</h3> |
|
|
<p class="text-gray-600 mb-2">Refined our evaluation criteria for legal research tasks to better assess citation accuracy and relevance.</p> |
|
|
<span class="text-sm text-gray-500">Posted: May 28, 2023</span> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
<div class="bg-gray-50 px-6 py-3 text-right"> |
|
|
<a href="#" class="text-legal-blue font-medium hover:underline">View All Updates →</a> |
|
|
</div> |
|
|
</div> |
|
|
</section> |
|
|
</main> |
|
|
|
|
|
|
|
|
<footer class="bg-legal-blue text-white py-12"> |
|
|
<div class="container mx-auto px-4"> |
|
|
<div class="grid grid-cols-1 md:grid-cols-4 gap-8"> |
|
|
<div> |
|
|
<h3 class="text-lg font-semibold mb-4">LLM4Law</h3> |
|
|
<p class="text-gray-300"> |
|
|
Independent benchmarking of local LLMs for legal applications by IP attorneys. |
|
|
</p> |
|
|
</div> |
|
|
<div> |
|
|
<h4 class="text-lg font-semibold mb-4">Navigation</h4> |
|
|
<ul class="space-y-2"> |
|
|
<li><a href="#" class="text-gray-300 hover:text-white transition">Home</a></li> |
|
|
<li><a href="#" class="text-gray-300 hover:text-white transition">Benchmarks</a></li> |
|
|
<li><a href="#" class="text-gray-300 hover:text-white transition">Methodology</a></li> |
|
|
<li><a href="#" class="text-gray-300 hover:text-white transition">About</a></li> |
|
|
</ul> |
|
|
</div> |
|
|
<div> |
|
|
<h4 class="text-lg font-semibold mb-4">Resources</h4> |
|
|
<ul class="space-y-2"> |
|
|
<li><a href="#" class="text-gray-300 hover:text-white transition">Dataset</a></li> |
|
|
<li><a href="#" class="text-gray-300 hover:text-white transition">Research Papers</a></li> |
|
|
<li><a href="#" class="text-gray-300 hover:text-white transition">Model Cards</a></li> |
|
|
</ul> |
|
|
</div> |
|
|
<div> |
|
|
<h4 class="text-lg font-semibold mb-4">Connect</h4> |
|
|
<div class="flex space-x-4"> |
|
|
<a href="#" class="bg-white bg-opacity-10 hover:bg-opacity-20 w-10 h-10 rounded-full flex items-center justify-center transition"> |
|
|
<i class="fab fa-twitter"></i> |
|
|
</a> |
|
|
<a href="#" class="bg-white bg-opacity-10 hover:bg-opacity-20 w-10 h-10 rounded-full flex items-center justify-center transition"> |
|
|
<i class="fab fa-linkedin-in"></i> |
|
|
</a> |
|
|
<a href="#" class="bg-white bg-opacity-10 hover:bg-opacity-20 w-10 h-10 rounded-full flex items-center justify-center transition"> |
|
|
<i class="fab fa-github"></i> |
|
|
</a> |
|
|
</div> |
|
|
<div class="mt-4"> |
|
|
<a href="mailto:contact@llm4law.com" class="text-gray-300 hover:text-white transition">contact@llm4law.com</a> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
<div class="border-t border-white border-opacity-10 mt-8 pt-8 text-center text-gray-300"> |
|
|
<p>© 2023 LLM4Law. All rights reserved.</p> |
|
|
</div> |
|
|
</div> |
|
|
</footer> |
|
|
|
|
|
<script> |
|
|
|
|
|
document.querySelectorAll('tbody tr').forEach(row => { |
|
|
row.addEventListener('click', function() { |
|
|
|
|
|
alert('Navigating to detailed view for ' + this.querySelector('td:first-child .text-gray-900').textContent); |
|
|
}); |
|
|
}); |
|
|
</script> |
|
|
<p style="border-radius: 8px; text-align: center; font-size: 12px; color: #fff; margin-top: 16px;position: fixed; left: 8px; bottom: 8px; z-index: 10; background: rgba(0, 0, 0, 0.8); padding: 4px 8px;">Made with <img src="https://enzostvs-deepsite.hf.space/logo.svg" alt="DeepSite Logo" style="width: 16px; height: 16px; vertical-align: middle;display:inline-block;margin-right:3px;filter:brightness(0) invert(1);"><a href="https://enzostvs-deepsite.hf.space" style="color: #fff;text-decoration: underline;" target="_blank" >DeepSite</a> - 🧬 <a href="https://enzostvs-deepsite.hf.space?remix=JJ404GO/llm" style="color: #fff;text-decoration: underline;" target="_blank" >Remix</a></p></body> |
|
|
</html> |
