AI2 WildBench Leaderboard (V2)
Display and explore model leaderboards and chat history
Display and explore model leaderboards and chat history
Select and filter benchmarks for text embedding tasks
Track, rank and evaluate open LLMs and chatbots
Determine GPU requirements for large language models
Identify key entities in text
Browse and filter leaderboard of language models
Generate text from document images using prompts
Analyze document layout from images
Analyze documents to extract text and visualize segmentation
Answer questions about images by chatting
Efficient quantized retrieval over Wikipedia
Explore and analyze RewardBench leaderboard data
Identify objects in images based on text descriptions
Analyze images to detect and label objects
VLMEvalKit Evaluation Results Collection
Run a Streamlit web app
Visualize LLM progress with interactive filters
Upload a PDF and ask questions to get insights
Submit and evaluate models on a leaderboard
Identify and highlight key entities in text
Engage in conversations with a multilingual language model
Explore and analyze code evaluation data
Create a Hugging Face dataset from text files
Convert text to speech in multiple languages
Analyze images to generate captions, detect objects, or perform OCR
Generate React TypeScript App
Video captioning/tracking
Display Visual Document Retrieval leaderboard
In-browser speech recognition w/ word-level timestamps
Generate insights from charts using text prompts
Need to analyze data? Let a Llama-3.1 agent do it for you!
Teach, test, evaluate language models with MTEB Arena
View and submit language model evaluations
Detect objects in images and get bounding boxes
VLMEvalKit Eval Results in video understanding benchmark
Extract text from images using various OCR modes
Display and filter leaderboard results for LLM judges
remove background from any image
Compare AI models by voting on responses
What happened in open-source AI this year, and whatβs next?
Explore and submit LLM benchmark evaluations
Detect and annotate poses in images and videos
Create and run Jupyter notebooks interactively