Companion leaderboard for the SLM survey paper
Monitor application health
Explore token probability distributions with sliders
Browse and submit evaluation results for AI benchmarks
Display a welcome message on a webpage
Generate synthetic dataset files (JSON Lines)
Uncensored General Intelligence Leaderboard
Generate benchmark plots for text generation models
Calculate VRAM requirements for running large language models
Finance chatbot using vectara-agentic
Analyze and visualize data with various statistical methods
Analyze weekly and daily trader performance in Olas Predict
Compare classifier performance on datasets
SLM Leaderboard is a companion leaderboard for the SLM survey paper, designed to display and organize benchmark results from various models evaluated in the paper. It serves as a centralized platform for researchers and developers to track performance metrics and compare SLM (Specialized Language Models) across different tasks and datasets.
What does SLM stand for?
SLM stands for Specialized Language Models, which are language models tailored for specific tasks or domains.
Can I customize the leaderboard's appearance?
Yes, you can filter and sort the data to view specific models or tasks. However, the leaderboard itself is a static markdown table and cannot be altered in real-time.
How often is the leaderboard updated?
The leaderboard is updated periodically as new models or benchmark results are published in the SLM survey paper.