AI Model Library: LLMs, Agents & Dev Tools
Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.
Tag: Multimodal
111 article(s) found · Clear tag
PerceptionBench – Moonshot AI's Open-Source Visual Perception Diagnostic Benchmark
PerceptionBench is an open-source visual perception diagnostic benchmark launched by Moonshot AI, focusing on fine-grained evaluation of atomic-level visual perception capabilities. Starting from the ...
MiniMax H3 – A General-Purpose Multimodal Generation Model from MiniMax
MiniMax H3 is a general-purpose multimodal generation model officially released by MiniMax on July 31, 2026. This model breaks the boundaries between traditional tasks and modalities, achieving unifie...
FLUX 3 – A Multimodal Foundation Model Launched by Black Forest Labs
FLUX 3 is a multimodal foundation model launched by Black Forest Labs, which for the first time jointly learns images, videos, and audio under a unified architecture. Based on Self-Flow technology, th...
BigMac – Xiaohongshu's Open-Source Framework for Pipeline-Parallel Training of Multimodal Large Models
BigMac is an open-source pipeline-parallel training framework for multimodal large models developed by the dots infra team at Xiaohongshu. It aims to address the fundamental contradiction between comp...
Cosmos 3 Edge – NVIDIA's 4B Parameter Open-Source World Model
Cosmos 3 Edge is a 4B parameter open-source world model introduced by NVIDIA, specifically designed for real-time inference in robotics and edge AI. Based on the Nemotron architecture, the model integ...
SciReasoner – A Multimodal Foundation Model for Scientific Reasoning Developed by the Shanghai AI Lab and Others
SciReasoner is a new-generation multimodal foundation model for scientific reasoning, jointly developed by the Shanghai Artificial Intelligence Laboratory with teams from the Chinese University of Hon...
Mage-Flow – Microsoft's Open-Source Lightweight Multimodal Image Generation Model Series
Mage-Flow is a lightweight multimodal image generation model series open-sourced by Microsoft, based on a flow-matching architecture and featuring only 4B parameters. The model includes four variants:...
SenseNova-Vision – SenseTime's Open-Source Unified Vision Large Model for Understanding and Generation
SenseNova-Vision is an open-source unified vision large model developed by SenseTime, capable of both understanding and generating visual content. Its core innovation lies in natively integrating clas...
Inkling – A Multimodal Foundation Model from Thinking Machines Lab
Inkling is an open-weight multimodal foundation model developed by Thinking Machines Lab, utilizing a Mixture-of-Experts (MoE) architecture and natively supporting unified reasoning across text, image...
Muse Image – AI Image Generation Model by Meta Super Intelligence Lab
Muse Image is Meta Super Intelligence Lab's first self-developed AI image generation model, adopting an Agent architecture that collaborates with Muse Spark for multi-step planning and self-refinement...
Subscribe to AI Model Reviews
Get in-depth reviews the moment a new AI model drops. Know its capabilities and use cases.
We never share your email. Unsubscribe anytime.