MAI-Image keeps climbing! MAI Image 2.7 Preview is now #3 on @arena's image editing leaderboard. #2 by lab and ahead of GPT-Image-2. That's a +45 point jump from 2.6.
#Model releases#Image generation#Microsoft
Microsoft's MAI-Image-2.7-Preview takes #2 on AA-Image-Editing v2.1, close behind OpenAI's GPT Image 2.5 Sunburst (max) and a clear step up from MAI-Image-2.6 MAI-Image-2.7-Preview is Microsoft AI's newest image editing model, succeeding MAI-Image-2.6, released in August. In our testing, MAI-Image-2.7-Preview scores higher than MAI-Image-2.6 on all 7 editing actions we measure, and ranks #1 on 4 of them: Scene & Style Edit, Text or Symbol Edits, Reasoning-Based Edit, and Enhancement & Restoration. This new model improves on MAI-Image-2.6 with the biggest gains in Composition & Framing (+57 Elo), Text or Symbol Edits (+49) and Scene & Style Edit (+48). We see its best use cases to be in Live-Action Film, Consumer and Frontier edits, where it ranks #1. MAI-Image-2.7-Preview is available today in MAI Playground for image editing only, with text to image stated to be coming soon. Congratulations to @MicrosoftAI on the release! See below for our detailed analysis and example outputs of MAI-Image-2.7-Preview in the Artificial Analysis Image Arena 🧵
#Evaluations / benchmarks#Image generation#Microsoft
This is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.
#Model releases#Multimodal#Video
English text is being prepared.
#Model releases#Multimodal#Embodied AI
#Model releases#Open-source ecosystem#Hugging Face
Introducing 𝙻𝙵𝙼𝟹: our new generation of Liquid Foundation Models. With a new tri-hybrid architecture and new multimodal encoders, the LFM3 family is the ideal model suite for specialized intelligence. > 6 model instances, across text, audio, vision, and omni modalities, generative and decision models. > 𝙻𝙵𝙼𝟹-𝟷.𝟽𝙱: text, 256k context window. > 𝙻𝙵𝙼𝟹-𝚅𝙻-𝟸𝙱: vision-language model with video-input support for spatial understanding > 𝙻𝙵𝙼𝟹-𝙰𝚞𝚍𝚒𝚘-𝟸𝙱: tool calls, voice chat, reasoning in 18 languages. > 𝙻𝙵𝙼𝟹-𝙾𝚖𝚗𝚒-𝟸𝙱: an omni model combines vision, audio, and language. > 𝚍𝟷-𝟸𝙱 and 𝚍𝟷-𝙾𝚖𝚗𝚒-𝟸𝙱: decision models with typed outputs and calibrated probabilities in a single pass. Omni adds audio input. > fine-tune on 1 GPU. > a new tri-hybrid architecture > architecture optimized for 14 processor classes across GPUs, CPUs, and NPUs. > 𝙻𝙵𝙼𝟹-𝚅𝙻-𝟸𝙱 is a beast. It performs competitively with Gemma 4 12B (6x larger), and Gemini 3.5 Flash Lite, and GPT-5.6 Luna, with 1.9B parameters. > 𝙻𝙵𝙼𝟹-𝟷.𝟽𝙱 is #1 on the Pareto frontier of device intelligence 𝚙𝚒𝚙𝚎𝚝𝚝𝚎.𝚕𝚒𝚚𝚞𝚒𝚍.𝚊𝚒 Every modality for specialized intelligence. Pick the one that fits your use case, customize it, and run it on-device. 1/ 🧵
#Model releases#Open-source ecosystem#Agents
This is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.
#Model releases#Multimodal#Google
#Model releases#Multimodal#Google
#Model releases#Multimodal#Google
#Evaluations / benchmarks#Image generation#Microsoft
#Model releases#Reasoning#Open-source ecosystem
#Model releases#Open-source ecosystem#English text is being prepared.
Google DeepMind has released Genie 4, a new-generation general-purpose world model. For the first time in the Genie series, it natively generates ambient sound and improvised character dialogue, doubles the duration of a single coherent world to about 2 minutes, and renders real-machine footage at about 24 frames per second. The model uses Gemini 3.8 Flash to perform multi-step reasoning and control in the background and Gemini 4 Argon to break down action instructions, forming a hybrid world model architecture. It has opened beta applications to Google AI Ultra users and is also available in the Gemini API and Google AI Studio.
#Model releases#Multimodal#Video
OpenAI has launched a new model, GPT-6.1 Terra, focused on visual reasoning, computer operation, and writing capabilities. Its standard API price is $1 per million input tokens and $5 per million output tokens, 50% lower than GPT-5.6 Terra and GPT-6.1 Sol. At medium reasoning effort on Agents' Last Exam, its computer operation score is 15 percentage points higher than GPT-5.6 Terra, performing on par with GPT-6 Astra, while its price per token is only one-tenth of the latter's. The model is now available to Plus, Pro, Enterprise, and Edu users of ChatGPT Work and Codex, and its factual error rate drops to 4.3% at the highest reasoning effort.
#Model releases#OpenAI#Reasoning
On October 27, Liquid AI released the LFM3 series. All six 2B-parameter-class open-weight models branch from the same LFM3-1.7B-Base, covering text, vision, audio, omni-modal, and decision models. LFM3-1.7B has 1.73B parameters, a 256K token context, supports 16 languages, and adopts a Tri-Hybrid architecture with 13 layers of gated short convolutions, 5 layers of sliding-window attention, and 6 layers of global attention. It is available under the LFM Open License v1.0 on Hugging Face, the Liquid AI Playground, and via API. The company claims that LFM3-1.7B surpasses LFM2.5-2.6B with 35% fewer parameters and occupies about 1 GB of memory at 4-bit precision, but the model card states that it is not suitable for agentic coding or complex multi-step reasoning.
#Model releases#Open-source ecosystem#Multimodal
Google previews the Genie 4 world model, which can generate realistic three-dimensional environments based on natural language descriptions and supports editing operations such as changing the weather and adding objects with follow-up prompts. Compared with the previous generation, Genie 4 is better at rendering complex details such as fluid motion, can also generate accompanying audio such as crashing waves, and makes virtual characters move naturally and be controllable through real-time interaction. Internally, the model calls Gemini Omni to ensure visual realism and Gemini 3.8 Flash to maintain inter-frame consistency. It is currently being tested with a small number of early users and will later be offered through the Google AI Ultra subscription, the Gemini API, and Google AI Studio.
#Model releases#Multimodal#Google
Google DeepMind has released the Genie 4 world model, which can render interactive environments in real time with simulated physics, human motion, and native audio, with Gemini Omni shaping the scenes and Gemini 3.8 Flash planning the next steps. Genie 4 lets developers generate testing environments on demand, for scenarios such as the Apptronik Apollo humanoid robot playing checkers, but Google acknowledges that its physics is not always accurate, and objects may shift or behave abnormally during long runs. Google has not yet published benchmark data for Genie 4 in repeated agent testing, including whether the same prompt can produce consistent results.
#Model releases#Multimodal#Agents
Google DeepMind launches Genie 4, the successor to Genie 3. It is its first real-time world model capable of directly generating sound, computing scenes frame by frame and responding to users' keyboard operations and text prompts. Gemini models handle planning in the background; for example, Gemini 3.8 Flash continuously observes the screen, breaks goals into steps, and checks the result of each step. DeepMind is also testing the use of Gemini 4 Argon to combine Genie with its robotics research Gemini Robotics; in a demo, it simulated the Apptronik humanoid robot Apollo playing chess. DeepMind says the model is still an early experimental version: visual details drift over long simulations, objects do not necessarily persist, and it is currently limited to select testers. All videos and audio tracks will carry a SynthID watermark.
#Model releases#Multimodal#Video
Google DeepMind launched the world model Genie 4 on Tuesday. Currently in research preview, it can generate interactive virtual worlds and modify scenes by entering prompts during simulation runs. The model can generate real-time audio synchronized with the virtual world, covering music, ambient sound, and interactive dialogue, and scenes can remain coherent for up to two minutes—twice as long as the previous generation, Genie 3. Genie 4 will be gradually opened to Google AI Ultra subscribers, the Genie program, and early partners of the Gemini API and Google AI Studio. The team also acknowledges that the longer the simulation runs, the more easily details drift, and that audio accuracy and on-screen text clarity remain unresolved.
#Model releases#Multimodal#Video
Google DeepMind has released the Genie 4 world model, positioned as a major research milestone, allowing users to use natural language instructions to change weather, camera, and characters in real time. It is DeepMind's first model to natively generate audio within real-time world simulation, with audio and visuals produced synchronously, and it shows stronger performance in physical scenarios such as aerodynamics and collisions as well as in character movements. Genie 4 is currently available only as a research preview to trusted testers, and in the coming weeks will expand to Project Genie for Google AI Ultra subscribers as well as early partners of the Gemini API and Google AI Studio; engineer Diego Rivas acknowledged that long-duration simulations may show detail drift, and that audio accuracy and the readability of in-frame text have not yet been fully resolved.
#Model releases#Multimodal#Video