Models

SenseTime's multimodal agent model, announced in Hong Kong in November 2026, aimed at office work and design generation: long-term memory, task execution, and output ranging from PPTX decks to Blender 3D scenes.

ChinaEnterpriseAgents & tool use

Nemotron 3.5 Transcribe is Nvidia's free, open-weight speech transcription model, released on 28 October 2026. It handles recordings up to an hour long, transcribes up to 40 languages and can separate up to eight speakers.

Open sourceMultimodalHardware & compute

PLaMo 3 Translate is a family of translation-specialised language models from Preferred Networks, released in four sizes from 0.8B to 31B parameters, covering 53 languages and shipping in several quantised formats.

Large language modelsOpen sourceFoundation models

LFM3-Omni-2B is Liquid AI's first omni-modal model in the LFM3 family: one 2.17-billion-parameter model that reads text, images, video and audio and answers in text or speech.

Large language modelsOpen sourceConsumer apps

Kling 4.0 is a text-to-video generation model released to all users in October 2026, adding longer shots, multi-image references and more convincing physical motion, alongside a faster Flash variant built for high-volume work.

ChinaMultimodalGenerative models

Muse Spark Open is Meta's open-weight large language model, announced on 15 October 2026. With 816 billion total parameters, it is built for coding and agentic work, and its weights can be downloaded, unlike the closed Muse Spark that started the family.

Large language modelsOpen sourceAgents & tool use

Mistral Large 4 is Mistral AI's flagship open-weight model, with about 1 trillion total parameters, a 1M-token context window and native multimodality. It was previewed on 6 October 2026, and an improved version's weights followed on 29 October 2026.

Large language modelsOpen sourceMultimodal

MiniMax-M3.1-Flash is a sparse mixture-of-experts model from MiniMax with about 428B total parameters, 23B activated per token, text, image and video input and up to 1M tokens of context, released on Hugging Face in October 2026.

Open sourceChinaAgents & tool use

PixVerse R2 is a real-time world model announced on 22 September 2026, an upgrade to R1 that keeps a navigable world generating while the user moves inside it and holds state across a session.

ChinaMultimodalGenerative models

Vidu S2 is a two-part video generation system: S2-Avatar renders interactive digital characters at 720p in real time, and S2-Editing transforms live video streams. Both also produce stereo views for immersive displays.

ChinaMultimodalGenerative models

DeepSeek-V4.1-Flash, released on 10 September 2026 under the API name deepseek-flash, is a 552-billion-parameter multimodal mixture-of-experts model with a causal encoder-decoder design and a 1M-token context.

Large language modelsOpen sourceChina

Step 5 Preview is a preview release of StepFun's flagship foundation model: a sparse mixture-of-experts system with 600 billion total parameters, a 1-million-token context window and published weights, released in September 2026.

Large language modelsChinaAgents & tool use

SenseNova U1.5 is SenseTime's open-weight, 8-billion-parameter model that handles image understanding, reasoning and native 4K generation in a single network, without separate vision encoders or VAEs. It is released under the Apache License 2.0.

Open sourceChinaMultimodal

Seedance 2.5, released by ByteDance in July 2026, is an audio-video joint generation model that makes clips of up to 30 seconds per pass, accepts many multimodal references, and supports editing parts of a scene without regenerating the whole clip.

ChinaMultimodalGenerative models

FLUX 3 is a multimodal model family from Black Forest Labs, announced on 23 July 2026, covering images, video, audio and action prediction. Its video model became generally available on 4 August 2026.

MultimodalRoboticsGenerative models

Inkling is the first model released by Thinking Machines Lab: a 975B-parameter mixture-of-experts model with open weights, native text, image and audio input, and a context window of up to 1M tokens.

Large language modelsOpen sourceMultimodal

GPT-Live-1 is OpenAI's full-duplex voice model family, launched 8 July 2026, which lets ChatGPT listen and speak at the same time and replaced the earlier chained speech pipeline in ChatGPT Voice.

Agents & tool useConsumer appsMultimodal

Vidu S1 is Shengshu's real-time interactive video generation model, released in July 2026. It takes spoken commands as control input, runs on consumer GPUs at 540p and up to 42 frames per second, and keeps generating without drift.

ChinaMultimodalGenerative models

ByteDance Seed's Seed2.1, released in June 2026 in Pro and Turbo versions, is a Doubao-family model aimed at real productivity work, with reported gains in agent ability, coding, knowledge, reasoning and multimodal understanding.

Large language modelsChinaAgents & tool use

Apple Foundation Models 3 (AFM 3), published on 8 June 2026, is a family of five models: two on-device models, including a sparse 20B multimodal model, and three cloud models, one of which is optimised for NVIDIA GPUs.

Large language modelsConsumer appsFoundation models

A mixture-of-experts language model released by MiniMax in June 2026, with about 428B total parameters, a 1M-token context window and a new sparse attention scheme built for long-context and agent-style work. [^1]

Large language modelsOpen sourceChina

Step 3.7 Flash is a StepFun open-weights model released on 29 May 2026. It adds native image input to Step 3.5 Flash, supports a 256K context, and is licensed under Apache 2.0.

Open sourceChinaAgents & tool use

Command A+ is Cohere's open-source mixture-of-experts language model, released on 20 May 2026 under the Apache 2.0 licence with 218 billion total and 25 billion active parameters, aimed at sovereign and critical-infrastructure deployments.

Large language modelsOpen sourceEnterprise

Gemini Omni Flash is a Google DeepMind generative model that makes and edits video from text, image, audio and video prompts. Video creation arrived in the Gemini app on 19 May 2026, and the model later became the recommended replacement for Google's Veo 3.1 API previews.

MultimodalGenerative modelsCreative tools

SenseNova U1 is SenseTime's open-weight multimodal model family, first released in April 2026 under Apache 2.0, which understands and generates images without a separate visual encoder or VAE.

Open sourceChinaMultimodal

π0.7 is a general-purpose robot manipulation model from Physical Intelligence that matches fine-tuned specialists on a wide range of dexterous tasks while following new language commands and recombining learned skills in unfamiliar settings.

Foundation modelsMultimodalRobotics

EXAONE 4.5 is LG AI Research's first open-weight vision language model: a 33-billion-parameter model with a 1.2-billion-parameter vision encoder, trained on documents and text, with a 256K-token context window, released in April 2026.

Large language modelsOpen sourceFoundation models

Muse Spark is the first model from Meta Superintelligence Labs, released on 8 April 2026 as a closed model that powers the Meta AI app and meta.ai. An open-weight sibling followed later.

Large language modelsAgents & tool useConsumer apps

Gemma 4 is Google's fourth generation of open-weight models, released in April 2026 and built on the same research and technology as Gemini 3, ranging from phone-sized E2B and E4B to a 26B mixture-of-experts and a 31B dense model.

Large language modelsOpen sourceMultimodal

A speech-to-text model from Microsoft AI released in April 2026 that transcribes 25 languages, runs Copilot's Voice Mode, and starts at $0.36 per hour of audio.

EnterpriseMultimodalCloud

Mistral Small 4 is an open-weight mixture-of-experts model released in March 2026 that folds instruction-following, step-by-step reasoning and agentic coding into one model, with a switch that controls how much reasoning it does.

Large language modelsOpen sourceMultimodal

Reka Edge is a 7-billion-parameter vision-language model from Reka AI, released on 11 March 2026, built to take images, video and text and to run locally on laptops, phones and small edge devices.

Open sourceMultimodalRobotics

Ai2's fully open 7B model, which mixes Transformer attention with Gated DeltaNet linear recurrent layers and matches its predecessor's MMLU accuracy using 49% fewer training tokens.

Large language modelsOpen sourceDeep learning

Phi-4-reasoning-vision-15B is Microsoft's 15-billion-parameter open-weight vision-language model, released on 4 March 2026 under the MIT licence, built to switch between step-by-step reasoning for math and science and direct answers for image perception tasks.

Open sourceMultimodalReasoning

Gemini 3.1 Pro is Google's preview upgrade to Gemini 3 Pro, released on 19 February 2026, scoring a verified 77.1% on ARC-AGI-2 and shipped through the Gemini API, the Gemini app and NotebookLM.

Large language modelsMultimodalReasoning

Qwen3.5 is a natively multimodal model family from Alibaba released in February 2026. Its open flagship, Qwen3.5-397B-A17B, has 397B total parameters and 17B active per token, under Apache 2.0.

Large language modelsOpen sourceChina

Seed2.0 is ByteDance's February 2026 Doubao model series, offered in three agent-oriented sizes with low token pricing and reported benchmark results.

Large language modelsChinaAgents & tool use

Kling 3.0 is Kuaishou's video and image model series, launched on 5 February 2026 as four models. It generates up to 15 seconds of video with simultaneous audio, adds multi-shot generation and supports native 4K output.

ChinaMultimodalGenerative models

Kimi K2.5 is a natively multimodal open-weight model from Moonshot AI, released on 27 January 2026. It has 1 trillion total parameters, a 256K-token context and an Agent Swarm feature for parallel sub-agents.

Open sourceChinaAgents & tool use

An audio-video generation model from Volcano Engine, announced on 18 December 2025, that produces picture, voices, music and ambient sound together and keeps them in millisecond-level sync.

ChinaMultimodalGenerative models

Doubao Large Model 1.8 (Doubao-Seed-1.8) is ByteDance's Volcano Engine flagship released on 18 December 2025. It is built for multimodal agent tasks, with stronger tool calling and computer-operation abilities.

Large language modelsChinaEnterprise

Molmo 2 is the second generation of Ai2's open vision-language models, released on 11 December 2025, which extends the Molmo line from still images to video with pointing, tracking and timestamped answers.

Open sourceMultimodalComputer vision

GWM-1 is Runway's first general world model: an autoregressive system that generates 720p video frame by frame in real time and can be steered with camera pose, robot commands or audio.

MultimodalRoboticsGenerative models

Kling 2.6 is a Kuaishou video generation model released in December 2025 that produces visuals, voiceover, sound effects and ambient audio in a single pass, with clips capped at 10 seconds.

ChinaMultimodalGenerative models

Three small dense models from Mistral AI — 3B, 8B and 14B — released in December 2025 under Apache 2.0, each in base, instruct and reasoning variants with image understanding.

Large language modelsOpen sourceMultimodal

Mistral AI's flagship model of the Mistral 3 family, released in December 2025: a sparse mixture-of-experts model with 675B total parameters, open weights under Apache 2.0, and image understanding.

Large language modelsOpen sourceFoundation models

Amazon Nova 2 is the second generation of Amazon's Nova models, released at AWS re:Invent in December 2025. Its first member, Nova 2 Lite, is a fast reasoning model available in Amazon Bedrock with a 1-million-token context.

Large language modelsAgents & tool useMultimodal

Kling O1 is a video model that Kuaishou announced on 1 December 2025. The company described it as the first unified multimodal video model: text, image, video and subject inputs go into one engine used both for generation and for editing.

ChinaMultimodalGenerative models

Runway Gen-4.5 is a video generation model released in December 2025 that topped the Artificial Analysis text-to-video leaderboard and later gained native audio, multi-shot editing and a role as the base for Runway's GWM-1 world model.

MultimodalGenerative modelsCreative tools

ERNIE 5.0 is Baidu's natively omni-modal foundation model, unveiled in November 2025 and described as having 2.4 trillion parameters. It is proprietary and was made available to enterprises and consumers in January 2026.

Large language modelsChinaFoundation models

Baidu's open-weight multimodal reasoning model from November 2025: 28B total parameters with 3B active per token, "Thinking with Images" zoom-and-tool reasoning, and Apache 2.0 weights.

Open sourceChinaMultimodal

DeepSeek-OCR is an open-source model of about 3B parameters that renders long text as 2D images and reads it back from a small number of vision tokens, testing whether optical compression can stand in for very long text contexts.

Open sourceChinaMultimodal

Veo 3.1 is an October 2025 update to Google's Veo 3 video model, adding audio across Flow's features plus new editing tools; its API previews were retired in October 2026.

MultimodalGenerative modelsCreative tools

An open-source image generation model from Tencent that handles image understanding and generation inside a single autoregressive mixture-of-experts framework; its code, weights and technical report were released in September 2025.

Open sourceChinaMultimodal

A pair of robotics models announced by Google DeepMind in September 2025: Gemini Robotics 1.5, a vision-language-action model that reasons in natural language before it moves, and Gemini Robotics-ER 1.5, an embodied-reasoning planner that can call tools.

Agents & tool useMultimodalRobotics

Ray3 is a video generation model released by Luma AI on 18 September 2025 and described by the company as the first reasoning video model, with HDR output, native 1080p and a neural upscaler to 4K.

MultimodalReasoningGenerative models

Qwen3-Omni is an open-weight multimodal model released by the Qwen team in September 2025 under Apache 2.0, able to take in text, audio and video and to answer in text or speech across many languages.

Open sourceChinaConsumer apps