Kling 3.0
Kuaishou's Kling 3.0 is the first commercially available AI video model to ship native 4K at 60fps, with multilingual audio, multi-shot storyboarding, and a $0.075/s API.
Articles Tagged "Multimodal"
Grok Imagine Video 1.5
xAI's Grok Imagine Video 1.5 is the #1-ranked image-to-video model on Artificial Analysis, generating 720p clips with native audio at $0.14/s - 86% cheaper than Sora 2 Pro.
Dreamina Seedance 2.0
ByteDance's top-ranked AI video generation model with native joint audio-video synthesis, multi-shot support, and multimodal reference inputs across up to 12 files per generation.
Wan 2.7
Alibaba's open-source video generation model with MoE architecture, native audio, first-and-last-frame control, and 1080p output up to 15 seconds.
HappyHorse-1.0
HappyHorse-1.0 is Alibaba's 15-billion-parameter video generation model that ranked #1 on Artificial Analysis, producing 720p-1080p clips with joint audio-video synthesis in a single forward pass.
SkyReels V4
SkyReels V4 is Skywork AI's unified multi-modal video model that jointly generates 1080p/32FPS video and synchronized audio from a single dual-stream diffusion transformer.
Sora 2
OpenAI's Sora 2 generates physics-accurate video with synchronized audio from text or images, available API-only until its September 24, 2026 sunset.
Runway Gen-4.5
Runway's Gen-4.5 is a video generation model built on an Autoregressive-to-Diffusion architecture that held the top Artificial Analysis Elo position at launch with 1,247 points before Seedance 2.0 and Kling 3.0 surpassed it in early 2026.
MAI-Transcribe-1.5
Microsoft's second-generation speech-to-text model with 2.4% WER, 43-language support, keyword biasing, and 5x faster long-audio processing than comparable accuracy models.
GPT-5.1
GPT-5.1 is OpenAI's November 2025 coding and agentic flagship with 400K context, configurable reasoning effort, and 76.3% on SWE-bench Verified.
Alibaba's Qwen-Robot Suite Targets Physical AI Work
Alibaba launches three open-weight models for robot manipulation, navigation, and world prediction, built on a shared Qwen3.5 backbone with open weights.
Qwen-RobotManip
Alibaba's generalist VLA model for robotic manipulation, built on Qwen3.5-4B with a DiT action decoder, trained on 38,100+ hours of open-source data, and ranked first on the RoboChallenge generalist track.
