LLM Model Releases - New AI Model Announcements Today
Latest AI model releases and announcements. GPT, Claude, Gemini, Llama, and more. Breaking news on new model launches.
News Feed
Qwen: Qwen3.5 Plus 2026-02-15 (qwen/qwen3.5-plus-02-15)
The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.
Qwen: Qwen3.5 397B A17B (qwen/qwen3.5-397b-a17b)
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.
Anthropic’s Super Bowl ads mocking AI with ads helped push Claude’s app into the top 10
The numbers suggest that Anthropic's Super Bowl commercials, combined with Anthropic's recent release of its new Opus 4.6 model, worked to drive attention to Claude's app and its key differentiator from ChatGPT.
[AINews] new Gemini 3 Deep Think, Anthropic $30B @ $380B, GPT-5.3-Codex Spark, MiniMax M2.5
There's too much going on!
Gemini 3 Deep Think: Advancing science, research and engineering
Our most specialized reasoning mode is now updated to solve modern science, research and engineering challenges.
Gemini 3 Deep Think: Advancing science, research and engineering
Gemini 3 Deep Think logo
MiniMax: MiniMax M2.5 (minimax/minimax-m2.5)
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.
[AINews] Z.ai GLM-5: New SOTA Open Weights LLM
We have Opus 4.5 at home
NVIDIA Nemotron 3 Nano 30B MoE model is now available in Amazon SageMaker JumpStart
Today we’re excited to announce that the NVIDIA Nemotron 3 Nano 30B model with nbsp;3B active parameters is now generally available in the Amazon SageMaker JumpStart model catalog. You can accelerate innovation and deliver tangible business value with Nemotron 3 Nano on Amazon Web Services (AWS) without having to manage model deployment complexities. You can power your generative AI applications with Nemotron capabilities using the managed deployment capabilities offered by SageMaker JumpStart.
Z.ai: GLM 5 (z-ai/glm-5)
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.
[AINews] Qwen Image 2 and Seedance 2
Strong generative media showings from China
Latam-GPT: a Latin American AI to combat US-centric bias
Move over ChatGPT. Chile on Tuesday launched Latam-GPT, an open-source artificial intelligence model for the region, designed to combat bias inherent in a US-centric industry.
Qwen: Qwen3 Max Thinking (qwen/qwen3-max-thinking)
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior.
More Topics
Related Pricing
Built by @aellman
Tools
Directories
Rankings
- All Rankings
- Best LLM for Coding
- Best LLM for Math
- Best LLM for Writing
- Best LLM for RAG
- Best LLM for OpenClaw
- Best LLM for Cursor
- Best LLM for Windsurf
- Best LLM for Cline
- Best LLM for Aider
- Best LLM for GitHub Copilot
- Best LLM for Bolt
- Best LLM for Continue.dev
- MMLU-Pro
- GPQA
- LiveCodeBench
- Aider
- AIME
- MATH (Hard)
- Big-Bench Hard
2026 68 Ventures, LLC. All rights reserved.