Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. With a 1T-parameter MoE architecture (32B active) and 256K context length, it seamlessly integrates vision and language understanding with advanced agentic capabilities, supporting both instant and thinking modes, as well as conversational and agentic paradigms...

GLM-4.6V achieves SOTA (State-of-the-Art) accuracy in visual understanding among models of the same parameter scale. For the first time, it natively integrates Function Call capabilities into the visual model architecture, bridging the gap between "Visual Perception" and "Executable Action." This provides a unified technical foundation for multimodal Agents in real-world business scenarios. Additionally, the visual context window has been expanded to 128k, supporting long video stream processing and high-resolution multi-image analysis....

Qwen3-VL is the vision-language model in the Qwen3 series, achieving state-of-the-art(SOTA)performance on various vision-language(VL)benchmarks. The model supports high-resolution image inputs up to the megapixel level and possesses strong capabilities in general visual understanding, multilingual OCR, fine-grained visual grounding, and visual dialogue. As part of the Qwen3 series, it inherits a powerful language foundation, enabling it to understand and execute complex instructions....

Qwen3-VL-Thinking is a version of the Qwen3-VL series specially optimized for complex visual reasoning tasks. It incorporates a "Thinking Mode" , enabling it to generate detailed intermediate reasoning steps (Chain-of-Thought) before providing a final answer. This design significantly enhances the model's performance on visual question answering (VQA) and other vision-language tasks that require multi-step logic, planning, and in-depth analysis....

Qwen3-VL-8B-Instruct is the vision-language model of the Qwen3 series, demonstrates strong capabilities in general visual understanding, visual-centric dialogue, and multilingual text recognition in images. ...

Qwen3-VL-8B-Thinking is a vision-language model from the Qwen3 series, optimized for scenarios requiring complex reasoning. In this Thinking mode, the model performs step-by-step thinking and reasoning before providing the final answer....

Qwen3-VL-235B-A22B-Instruct is a 235B parameters Mixture-of-Experts (MoE) vision-language model, with 22B activated parameters. It is an instruction-tuned version of Qwen3-VL-235B-A22B and is aligned for chat applications. ...

Qwen3-VL-235B-A22B-Thinking is one of the Qwen3-VL series models, a reasoning-enhanced Thinking edition that achieves state-of-the-art (SOTA) results across many multimodal reasoning benchmarks, excelling in STEM, math, causal analysis, and logical, evidence-based answers. It features a Mixture-of-Experts (MoE) architecture with 235B total parameters and 22B active parameters. ...

Qwen3-VL series delivers superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions....

Qwen3-VL series delivers superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions....

As a part of the GLM-V family of models, GLM-4.5V is based on ZhipuAI’s foundation model GLM-4.5-Air, achieving SOTA performance on tasks such as image, video, and document understanding, as well as GUI agent operations....

Qwen3-Omni-30B-A3B-Captioner is a Vision-Language Model (VLM) from Alibaba's Qwen team, part of the Qwen3 series. It is specifically designed for generating high-quality, detailed, and accurate image captions. Based on a 30B total parameter Mixture of Experts (MoE) architecture, the model can deeply understand image content and translate it into rich, natural language text...

Qwen3-Omni-30B-A3B-Instruct is a member of the latest Qwen3 series from Alibaba's Qwen team. It is a Mixture of Experts (MoE) model with 30 billion total parameters and 3 billion active parameters, which effectively reduces inference costs while maintaining powerful performance. The model was trained on high-quality, multi-source, and multilingual data, demonstrating excellent performance in basic capabilities such as multilingual dialogue, as well as in code, math...

Qwen3-Omni-30B-A3B-Thinking is the core "Thinker" component within the Qwen3-Omni omni-modal model's "Thinker-Talker" architecture. It is specifically designed to process multimodal inputs, including text, audio, images, and video, and to execute complex chain-of-thought reasoning. As the reasoning brain of the system, this model unifies all inputs into a common representational space for understanding and analysis, but its output is text-only. This design allows it to excel at solving complex problems that require deep thought and cross-modal understanding, such as mathematical problems presented in images, making it key to the powerful cognitive abilities of the entire Qwen3-Omni architecture...

Qwen2.5-VL-32B-Instruct is a multimodal large language model released by the Qwen team, part of the Qwen2.5-VL series. This model is not only proficient in recognizing common objects but is highly capable of analyzing texts, charts, icons, graphics, and layouts within images. It acts as a visual agent that can reason and dynamically direct tools, capable of computer and phone use. Additionally, the model can accurately localize objects in images, and generate structured outputs for data like invoices and tables. Compared to its predecessor Qwen2-VL, this version has enhanced mathematical and problem-solving abilities through reinforcement learning, with response styles adjusted to better align with human preferences...

Qwen2.5-VL is a vision-language model in the Qwen2.5 series that shows significant enhancements in several aspects: it has strong visual understanding capabilities, recognizing common objects while analyzing texts, charts, and layouts in images; it functions as a visual agent capable of reasoning and dynamically directing tools; it can comprehend videos over 1 hour long and capture key events; it accurately localizes objects in images by generating bounding boxes or points; and it supports structured outputs for scanned data like invoices and forms. The model demonstrates excellent performance across various benchmarks including image, video, and agent tasks...

Qwen2.5-VL is a new member of the Qwen series, equipped with powerful visual comprehension capabilities. It can analyze text, charts, and layouts within images, understand long videos, and capture events. It is capable of reasoning, manipulating tools, supporting multi-format object localization, and generating structured outputs. The model has been optimized for dynamic resolution and frame rate training in video understanding, and has improved the efficiency of the visual encoder....

DeepSeek-VL2 is a mixed-expert (MoE) vision-language model developed based on DeepSeekMoE-27B, employing a sparse-activated MoE architecture to achieve superior performance with only 4.5B active parameters. The model excels in various tasks including visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. Compared to existing open-source dense models and MoE-based models, it demonstrates competitive or state-of-the-art performance using the same or fewer active parameters....