Thinking Machines Lab releases Inkling, an open-weight 975B model
On 15 July 2026 Thinking Machines Lab released Inkling, an open-weight mixture-of-experts model with 975 billion total parameters. A smaller version followed on 31 July 2026.
Total 671 · Clear filters
OpenAI releases GPT-5.6 and ChatGPT Work
On 9 July 2026 OpenAI released GPT-5.6, a three-model family named Sol, Terra and Luna, together with ChatGPT Work for enterprise teams, and merged its Codex app into the ChatGPT desktop app.
OpenAI launches GPT-Live full-duplex voice in ChatGPT
On 8 July 2026 OpenAI launched GPT-Live, a generation of full-duplex voice models for ChatGPT that can listen and speak at the same time; the smaller model became ChatGPT's default voice model.
Mistral AI introduces Robostral Navigate for robots
On 8 July 2026 Mistral AI introduced Robostral Navigate, an 8-billion-parameter model that steers robots from camera images and spoken-style instructions, trained entirely in simulation and scoring 76.6% on a standard navigation benchmark.
Meta introduces Muse Image and Muse Video
On 7 July 2026 Meta Superintelligence Labs introduced Muse Image and Muse Video, its first media generation models. Muse Image launched in Meta's apps, while Muse Video entered early preview.
Tencent releases Hy3 under Apache 2.0 and integrates it across its products
On 6 July 2026 Tencent launched Hy3, a fast-and-slow-thinking reasoning model released under Apache 2.0 and integrated across its WorkBuddy, Yuanbao and ima products.
Shengshu releases the Vidu S1 real-time interactive video model
On 3 July 2026 Shengshu released Vidu S1, a real-time interactive video generation model that takes voice input during a video call and changes a character's expression, gestures and body movement in response.
Anthropic releases Claude Sonnet 5
On 30 June 2026 Anthropic released Claude Sonnet 5, its most agentic Sonnet model, at an introductory $2 and $10 per million tokens. On 10 August that price became permanent.
ByteDance releases Seed2.1
On 23 June 2026 ByteDance Seed announced Seed2.1 for Doubao and Volcano Engine users. It has Pro and Turbo models for productivity work and builds on Seed2.0.
Zhipu releases GLM-5.2 with a 1M-token context
On 16 June 2026 Zhipu released GLM-5.2 under the MIT License, expanding its context window to 1M tokens. The release reported gains over GLM-5.1 on reasoning and coding benchmarks.
Anthropic releases Claude Fable 5 and Claude Mythos 5
On 9 June 2026 Anthropic released Claude Fable 5, its first Mythos-class model for general use, and Claude Mythos 5, the same model with some safeguards lifted for vetted partners. Both were priced at $10 and $50 per million tokens.
Apple introduces AFM 3 and Siri AI at WWDC 2026
On 8 June 2026, at WWDC, Apple introduced AFM 3, its third generation of foundation models, and Siri AI, a more personal assistant for iOS 27. Developer testing began the same day, and the launch was limited in the EU and China.
NVIDIA releases Nemotron 3 Ultra, a 550B open model
On 4 June 2026 NVIDIA released Nemotron 3 Ultra, the largest model in its Nemotron 3 family, with 550 billion total parameters and 55 billion active per token.
Suno raises over $400 million in Series D at a $5.4 billion valuation
Suno announced on 3 June 2026 that it had raised more than $400 million in Series D funding, valuing the AI music company at $5.4 billion post-money, with Bond Capital leading the round.
Microsoft AI launches seven MAI models led by MAI-Thinking-1
On 2 June 2026 Mustafa Suleyman announced seven new in-house MAI models at Microsoft Build, led by the reasoning model MAI-Thinking-1. The group also included coding, image, transcription and voice models, and a healthcare collaboration with Mayo Clinic.
MiniMax releases natively multimodal MiniMax-M3 with sparse attention
In June 2026 MiniMax released M3, a natively multimodal model with about 428 billion total parameters, 1-million-token context and a new attention method, MiniMax Sparse Attention. MiniMax reported 9 times faster prefill and 15 times faster decoding than M2 at full context.
StepFun releases Step 3.7 Flash
On 29 May 2026 StepFun released Step 3.7 Flash under the tagline "The new frontier is agent efficiency". The model adds image understanding to Step 3.5 Flash and introduces an Advisor Mode for agent tasks.
Anthropic releases Claude Opus 4.8
On 28 May 2026 Anthropic released Claude Opus 4.8, a modest improvement on Opus 4.7 at the same price. Fast mode became three times cheaper, and Claude Code gained dynamic workflows that run hundreds of parallel subagents.
OpenBMB publishes MiniCPM5-1B
OpenBMB published MiniCPM5-1B on 21 May 2026, the first model in the MiniCPM5 series: a dense 1B Transformer for on-device use, with Apache-2.0 weights and UltraData training data.
Stability AI releases Stable Audio 3.0
In May 2026 Stability AI released Stable Audio 3.0 in four sizes, three of them open-weight. The two larger models generate up to 6 minutes 20 seconds of audio and support inpainting and continuation.
Cohere releases Command A+ as an Apache 2.0 open model
On 20 May 2026 Cohere released Command A+ as an Apache 2.0 open model with 218 billion total parameters. It was aimed at sovereign and critical-infrastructure users.