Termsslug: native-multimodality

Native Multimodality

原生多模态

Models trained from scratch to process text, images, and other modalities within a unified framework.

Curated Intelligence

15 items · Page 1/2
IT之家 · 智能时代T2·Models
78 pts
Ant Group Releases Ling 3.2 Flash Multimodal Model, Topping Claude Opus 5 on Three Benchmarks

Ant Group's Ling team released Ling-3.2-flash, a natively multimodal model built on a 560B-total / ~25B-active MoE architecture with a 1M context window and image, text and video input. In vendor-run tests it beats Claude Opus 5 on OmniDocBench1.5, ZEROBench and Vision2Web, and enters the DesignArena image-to-frontend top ten at 1238 Elo. API pricing is $0.30 per million input tokens and $0.90 per million output tokens, compatible with OpenAI and Anthropic protocols, and free for the first two weeks.

Hacker News AIT2·Models
92 pts
Moonshot AI Releases Open-Weight Kimi K3.1 Pro with 2.8T MoE Architecture

Moonshot AI has released the open-weight Kimi K3.1 Pro, its most capable 3T-class native multimodal agentic model to date. Featuring a Mixture-of-Experts architecture with 2.8T total parameters and 104B activated parameters, it supports a 1-million-token context window. Post-trained via large-scale joint reinforcement learning, the model delivers substantial improvements in coding, 3D creation, financial research, and factual accuracy.

Hacker News AIT2·Models
85 pts
LongCat-2.5 Launches: 1.6T MoE Model Boosts Long-Horizon Agentic Tasks

Meituan's LongCat team released LongCat-2.5, a native multimodal model with 1.6 trillion total parameters and ~48 billion activated per token. The update focuses on enhancing visual understanding and agentic coding, leveraging large-scale long-horizon reinforcement learning to improve end-to-end engineering capabilities for complex codebase development and full-project builds.

Hacker News AIT2·Models
88 pts
DeepMind Unveils Genie 4 for Multimodal Real-Time World Simulation

DeepMind has released Genie 4, a new native multimodal world model that synchronously generates visuals, audio, and interactive dialogue. By integrating capabilities from the Gemini family, Genie 4 significantly enhances realism and coherence in real-time interactive simulations, marking a crucial step toward AGI. Users can currently join a waitlist for early access.

新智元 (微信公众号)T2·Models
85 pts
Meta Open-Sources 816B Multimodal Model Runnable on Two Mac Studios

Meta has open-sourced Muse Spark Open, an 816-billion parameter multimodal model claimed to be the strongest open-weight model from the US. It supports a 1-million token context and native audio/video processing, optimized for complex coding and long-horizon reasoning. The key breakthrough is its accessibility: it can run locally on just two Apple Mac Studios, eliminating the need for cloud infrastructure or API costs.

IT之家 · 智能时代T2·Models
92 pts
Meta Releases Muse Spark Open: 816B MoE Model with 1M Context Runs Locally on Dual M5 Ultra Macs

Meta has released Muse Spark Open, a native multimodal model with 816B total parameters (42B active) and a 1M-token context window, claiming it as the strongest US open-weight model. Optimized for coding and agents, it uniquely supports local execution on just two Apple M5 Ultra Mac Studios and is available via major cloud APIs and inference engines.

Artificial Analysis (@ArtificialAnlys)T1·Models
58 pts
HiDream-O1-Video-1.0 Debuts at #6 on Image-to-Video Leaderboard with Native Audio and Dynamic Duration

HiDream has released HiDream-O1-Video-1.0, a native omnimodal video model ranking #6 on the Artificial Analysis Image-to-Video with Audio leaderboard. The model focuses on physical consistency, generating 1080p videos (5-20 seconds) with natively synchronized audio where duration is determined by scene content rather than fixed presets. It is currently available via the HiHarness API at $5.80 per minute.

IT之家 · 智能时代T2·Models
28 pts
Xiaomi Deprecates MiMo V2.5 Models, Mandating Switch to V2.6 Pro and Flash by October

Xiaomi announced the deprecation of its open-source LLMs MiMo-V2.5-Pro and MiMo-V2.5 in October 2026, requiring users to migrate to the newly released MiMo-V2.6 series. The V2.6 lineup features native multimodal Pro and Flash models, retaining the previous API pricing structure to deliver comparable intelligence at a fraction of overseas costs.