Arena Leaderboard
π
4.93k
View the LMArena leaderboard in fullβscreen
LLM Tools
A collection of tools as various HF Spaces on LLMs.
-
-
Open LLM Leaderboard
π14kTrack, rank and evaluate open LLMs and chatbots
-
OpenVoice
π€1.13kGenerate speech in a cloned voice from a short audio clip
-
Yet Another LLM Leaderboard
π192Launch a Streamlit web app interface
-
Phixtral Chat
π77 -
Hallucinations Leaderboard
π₯145View and submit LLM evaluations
-
WhisperSpeech
π¬377 -
Chunk Visualizer
π«232Pick a text splitter => visualize chunks. Great for RAG.
-
Modelcard Creator
β‘124Create a model card for Hugging Face Hub
-
LLM-Perf Leaderboard
π588Compare LLM hardware performance and find the best model
-
LLM Safety Leaderboard
π₯93Search, filter and submit LLM benchmark evaluations
-
LLaMA Board
π¦216Fine-tuning large language model with Gradio UI
-
ReplaceAnything
π954Replace objects in images using prompts or reference images
-
AutoMerger
βΎ72 -
Parler-TTS
π₯848High-fidelity Text-To-Speech
-
GLiNER-Multiv2.1
π»107Identify named entities in text
-
Ratchet + Phi
π61Generate AI responses to any text prompt
-
IDEFICS2 Playground
π¨169Chat with a visual AI that answers questions about images
-
PaliGemma Demo
π€²315Annotate and describe images with text prompts
-
GLiNER-medium-v2.1, zero-shot NER
π»177Extract custom entities from any text
-
GLiNER HandyLab
β‘86Perform multiple NLP tasks like NER, QA, and summarization
-
PDF to Dataset
π102Convert PDFs to a Hugging Face dataset
-
Instruction Synthesizer
π86Generate instruction-response pairs from text
-
GGUF My Repo
π¦1.99kQuantize Hugging Face models to GGUF format instantly
-
MeshAnything
π167Generate artist-style 3D meshes from any input model
-
Mars5 Space
π60 -
InternLM XComposer
π’163Display a web page
-
Built-in AI Chat
π38Run Gemini Nano locally in your browser with Transformers.js
-
Florence 2
π17Answer questions about images using text prompts
-
The Tokenizer Playground
π678Experiment with and compare different tokenizers
-
Whisper Speaker Diarization
π£330Generate speakerβlabeled transcripts from audio files
-
NIST FRVT TOP 1 Face Recognition, Face Liveness Detection, Face Analysis
π₯600Compare two faces to verify identity
-
Segment Anything 2
π₯143Segment images with prompts or automatic masks
-
Vision Papers
π»116All paper summaries read by Merve
-
FLUX.1 [Schnell]
π5.07kGenerate images from text prompts instantly
-
FLUX.1 [dev]
π₯9.48kGenerate images from text prompts
-
WebLLM Playground
π59Display a React app with TypeScript
-
Pdf Reader
π5Summarize text from a PDF URL
-
Falcon Mamba Playground
π65Generate chat responses using FalconMamba-7b model
-
LongWriter
π¬163LLM for long context
-
Llama3.1 S V0.2 Checkpoint 2024 08 20
π»115Chat with Llama3.1 using spoken audio or synthesize speech
-
Candle Phi Wasm Demo
π―122Generate text based on prompts
-
Latent Navigation
πͺ282Travel through the model latent space
-
reviewer-arena
π11Upload a paper to get reviews and vote on quality
-
Semantic Hugging Face Hub Search
π91Find datasets and models using semantic search
-
Convert to Safetensors
πΆ266Convert models to Safetensors and open a PR
-
Fish Audio S1
π697Convert text to natural-sounding speech audio
-
coreml-projects/sam-2-studio
Updated β’ 28 -
dleemiller/word-llama-l2-supercat
Updated β’ 92 -
PDF2Audio
π458Generate audioβready script from documents
-
Gemini 1.5 Flash 8b Exp 0924
π3Chat with a language model
-
Whisper WebGPU
π€260Transcribe audio files into readable text
-
Whisper Turbo
π€―1.02kTranscribe audio or YouTube videos into text
-
Rag Highlights
π14RAG with source links inserted using LXT library.
-
GOT Online
π¬360Extract and format text from images with advanced OCR
-
Kotaemon
π204Ask questions and get detailed answers
-
Semantic Deduplication
π§Ή39Deduplicate HuggingFace datasets in seconds
-
Ichigo Llama3.1 S Instruct
π’64Generate text from audio recordings
-
Qwen 2.5 Code Interpreter
π146Run code and get instant results with Qwen Code Interpreter
-
PROMPT++
β240Refine your prompts
-
Aya Models
π336Interact with the Aya family of models.
-
Open LLM Leaderboard Model Comparator
π113Compare Open LLM Leaderboard results
-
BitNet.cpp
π»18Display a loading screen with a spinner
-
MLX My Repo
π203Convert Hugging Face models to MLX format and upload
-
Vectorsearch Hub Datasets
π₯72Add vectors to Hub datasets and do in memory vector search.
-
sentence-transformers-testing/stsb-bert-tiny-lora
Sentence Similarity β’ Updated β’ 3 -
Talk To Ultravox
β‘38Talk to Fixie.ai's Ultravox with WebRTC β‘οΈ
-
Hub LFS Analysis
π19An analysis of LFS files on the Hub.
-
DocLayout YOLO
π190Demo for DocLayout-YOLO
-
Llmlingua 2
π»139Compress prompts while preserving key tokens
-
InstantIR
πΌ85diffusion-based Image Restoration model
-
Flux IP Adapter
πΌ170Prompt with Images in flux[dev]
-
Github Issue Generator
π§56Generate structured GitHub issues
-
Paligemma2 Vqav2
π¨48PaliGemma2 LoRA finetuned on VQAv2
-
Keras Chatbot Battle
π¬10Interact with multiple chatbots simultaneously
-
StoryStar
π¬24Fantasy story generator
-
Jupyter Agent
π313Generate executable Jupyter notebooks from natural language prompts
-
QwQ-32B-Preview
π921QwQ-32B-Preview
-
Qwen2.5 Coder Artifacts
π’1.73kGenerate and preview app code from a text description
-
Transformers Pipeline Playground
π10Search, load and play with transformer pipelines
-
Stable Point-Aware 3D
β‘468Generate 3D models from images
-
Fairly Multilingual ModernBERT Token Alignment
π15Aligns the tokens of two sentences
-
Kokoro TTS
β€3.38kUpgraded to v1.0!
-
Llama 3.2 Reasoning WebGPU
π§231Small and powerful reasoning LLM that runs in your browser
-
MiniMaxText01
π¬124Chat with an AI assistant (text and images)
-
Naive RAG Chatbot
π27Quickest way to test naive RAG run with AutoRAG.
-
DeepSeek-R1 WebGPU
π§557Next-generation reasoning model that runs locally in-browser
-
SmolVLM
π67Generate descriptions from images and text prompts
-
Janus Pro WebGPU
π215In-browser unified multimodal understanding and generation.
-
Agent Data Analyst
π€144Need to analyze data? Let a Llama-3.1 agent do it for you!
-
Kokoro TTS Zero
π΄311β¨[With v1.0.0] Accelerated TTS on Kokoro-82M
-
First Agent Template
β‘697Answer questions and run tools with an AI agent
-
Paligemma2 Mix
π97Generate text answers or segment objects from images
-
The Ultra-Scale Playbook
π3.9kThe ultimate guide to training LLM on large GPU Clusters
-
marimo github notebooks on the fly
β4Collection of marimo notebooks from a GitHub repository
-
Fastphone
π2Download and run a Hugging Face app
-
Magma UI
π47Magma-8B model for UI Agents
-
Deepseek Ai DeepSeek R1 Distill Qwen 32B
β‘8Answer questions using advanced AI
-
DiβͺβͺRhythm
πΆ688Blazingly Fast and Embarrassingly Simple Song Generation
-
Radial Plot Generator
πΈ7Generate radial plots comparing language model performance
-
OpenStreetMap AI Helper
π11Contributing to OpenStreetMap with the help of AI
-
DeTikZify
π90Convert images and sketches into graphics programs with TikZ
-
Bulk
π3A bulk labelling interface for binary text classification
-
DeepSite v4
π³16.6kGenerate any application by Vibe Coding it
-
YourBench
π44Generate custom evaluations from your data easily!
-
Dia 1.6B
π―1.78kGenerate realistic dialogue from a script, using Dia!
-
Qwen3 Demo
π857Chat with an AI assistant that thinks before answering
-
PlayDiffusion
π¨120Generate modified audio from text and voice
-
Conversational WebGPU
π234 -
Chatterbox TTS
πΏ1.74kExpressive Zeroshot TTS
-
Sheets
π649Create and enrich datasets using AI and web search
-
Leaderboard: Physical Reasoning from Video
π50Submit model evaluations and view leaderboard results
-
Nanonets Ocr S
π35https://nanonets.com/research/nanonets-ocr-s/
-
Gemma3n Visual (Audio) Question Answering
π»12Visual Audio Question Answering
-
Qwen3 MT Demo
π121Translate text instantly between many languages
-
Multimodal OCR2
π»143FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
-
Image To Prompt
π»771Generate detailed captions for your images
-
Qwen Image Edit
β826Edit images using natural language instructions
-
Example Leaderboard Template
π₯16Duplicate this leaderboard to initialize your own!
-
MatchAnything
π’260Find similar images and match them across collections
-
AnyCoder
π3.29kGenerate code snippets with AI for web and app frameworks
-
FastVLM WebGPU
π446Real-time video captioning powered by FastVLM
-
Semantic Galaxy
π151Visualize embeddings in 3D space, powered by EmbeddingGemma
-
Transformers Timeline
π€80Interactive timeline to explore the π€Transformers models
-
granite-docling-258M demo
π277Convert and query documents from images with AI
-
Granite-4.0 WebGPU
πͺ¨178Run Granite-4.0-Micro 100% locally in your browser on WebGPU
-
Granite Docling 258M WebGPU
π£160Convert document images to HTML with a single click
-
Qwen Image Edit Camera Control
π¬2.23kFast 4 step inference with Qwen Image Edit 2509
-
Qwen Image Edit Camera Control
π¬35Fast 4 step inference with Qwen Image Edit 2509
-
CUGA Agent
π€105Configurable Generalist Agent, leader in AppWorld Benchmark
-
Qwen3-TTS Demo
π1.99kGenerate speech from text using voice design, cloning or presets
-
Qwen3-ASR Demo
π140Transcribe audio to text with timestamps and visualization
-
GPT OSS WebGPU
β‘72Run GPT-OSS-20B locally in your browser on WebGPU
-
microgpt Playground
π§±68Build, train, and run LLMs in the browser
-
LFM2.5 1.2B Thinking WebGPU
π§120Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
-
Olmo Hybrid WebGPU
π¦13Run Olmo-Hybrid-7B 100% locally in your browser on WebGPU
-
LuxTTS
π109Space for LuxTTS: a 150x realtime voice cloning TTS model
-
Bonsai Image WebGPU
π³304State-of-the-art image generation, in your browser.