METRMETR conducts independent evaluations and research on frontier AI capabilities and risks, including autonomous capability assessments and safety policy analysis.(0)0
Text Generation WebUIRun large language models locally with Text Generation WebUI — supports text, vision, tool-calling, and fine-tuning. 100% offline, open source, and private.(0)0
Hallucinations LeaderboardExplore, filter, and compare large language models ranked by hallucination rates. Search models by name, precision, and type, or submit new models to the leaderboard.(0)0
Edge AI and Vision AllianceExplore expert articles, webinars, and market analysis on edge AI and computer vision. Join the Alliance community and attend the Embedded Vision Summit.(0)0
Chatbot ArenaChat with and compare top AI models like ChatGPT, Claude, and Gemini side-by-side. Vote on responses to shape the world's leading crowdsourced LLM leaderboard.(0)0
LiteRTDeploy ML and GenAI models on billions of edge devices with LiteRT, Google's high-performance on-device AI framework with GPU/NPU acceleration.(0)0
IBM AI Analog ComputeExplore IBM Research's AI platform featuring open-source Granite foundation models, generative computing research, and enterprise-ready trustworthy AI toolkits.(0)0
TensorRT LLM NVIDIANVIDIA TensorRT is an SDK for optimizing and accelerating deep learning inference on NVIDIA GPUs, featuring TensorRT-LLM, quantization tools, and up to 36x speedup over CPU.(0)0
M MLCommons AILuminateAILuminate by MLCommons benchmarks the safety of general-purpose AI chat models against malicious and self-harm prompts, with graded results across top AI vendors.(0)0
Apollo ResearchApollo Research evaluates frontier AI models for dangerous capabilities and scheming behaviors, providing technical research and expert guidance to global policymakers and AI developers.(0)0
