AI MODELS

Qwen3.8-27B is a 27B dense Apache-2.0 model that scores 61.7 on SWE-bench Pro and 42.2 on DeepSWE 1.1 - ahead of Opus 4.6 Max on both - while running on consumer hardware. Benchmarks, hardware math, and an honest when-to-use-it guide.

xAI shipped Grok 4.6 on August 12, 2026: it matches GPT-5.6 Sol on the AA Intelligence Index (61), beats it on CursorBench 3.2, and keeps Grok 4.5's $2/$6 per million token pricing. Available in Cursor and Grok Build today, and in OpenCode as opencode/grok-4.6.

Liquid AI released LFM2.5-VL-3B on August 12, 2026: a 3.1B open-weights vision-language model that averages 80.7 on ScreenSpot-v2, doubles ToolSandbox to 59.5, and decodes at 228 tokens/s on an M5 Max in about 3 GB of memory. Here is what shipped, the benchmark caveats, and how to run it.

Cactus open-sourced Needle 2, a 45M-parameter agentic LLM in a single 14MB binary that runs a full tool-calling session in 28MB of RAM. 500 tok/s on a Raspberry Pi 5, ESP32-S3 class parts, Apache 2.0. Here is what the benchmarks actually show.

A new arXiv paper shows the encrypted reasoning blocks that Anthropic, OpenAI, and Google return to API clients can be replayed into weaker models from the same provider and transcribed verbatim. The authors decoded 315,320 blocks from public repositories and recovered 367 PII artifacts and 182 credentials.

Meta open-sourced Muse Glimmer, a 30B Apache 2.0 multimodal agent model that runs in a 24GB envelope at up to 233 tok/s. MCP Atlas 75.5, SWE-Bench Verified 76.0, 131K context. Here is what the numbers actually say.

xAI released Grok Imagine Image 2.0 on August 7 as the new Quality Mode on grok.com and mobile, ranked second worldwide on both text-to-image and image-editing leaderboards. A 2.0 preview build is already callable through Vercel's AI Gateway with the AI SDK, before xAI's own API access goes live.

WeatherNext Cyclones adds a full day of lead time to tropical cyclone forecasts - roughly a decade of meteorological progress - and now the weights, code, and data feeds are public. What the paper actually shows and how to run it.

GitHub made Kimi K3 generally available in Copilot on August 6 at $3/$15 per million tokens, hosted on Fireworks AI. It is off by default for Business and Enterprise, the rollout was paused mid-day by a GitHub Actions incident, and it changes the price/quality calculus in the model picker.

Meta released Muse Code, a terminal coding agent, and Muse Spark 1.2 on August 5, 2026. The model co-trains with the harness, logs every call to a replay-safe event log, and offers a $0.10/$0.20 contributor tier if Meta may train on your data.

GPT-5.6 Sol gets a chat-focused retune with 68% fewer factual errors in OpenAI's internal eval, a new effort slider, and GPT-5.6 Luna becomes the default model for Free and Go users with unlimited text chats. What the API did not change and why the split matters.

Liquid AI shipped LFM2.5-2.6B on August 4, 2026: a 2.6B open-weight model trained for agentic work inside real harnesses, decoding at 220 tokens/s on an M5 Max and 113 tokens/s on a Ryzen CPU. Here is how it was trained, what the benchmarks say, and how to run it.

Alibaba released Qwen 3.8 Max on August 3, 2026 - a 2.4T-parameter MoE with 95B active per token, a 1M context window, and $2/$6 per million tokens on QwenCloud. It leads PaperBench at 93.0, and the weights open next week.

GitHub deprecated Gemini 2.5 Pro and Gemini 3 Flash in every Copilot surface on July 31, 2026. The suggested replacements are Gemini 3.1 Pro and Gemini 3.6 Flash. Here is what changed, what it costs, and how to migrate cleanly.

An analysis from the Earendil team behind the Pi harness documents how OpenAI, Anthropic, and Google now return provider-sealed state instead of portable transcripts - encrypted reasoning blobs, opaque compaction, hidden subagent messages. The five tests and seven rules for session portability, and why session lock-in matters more than model lock-in.

The sub-$1.50 coding tier just got serious: DeepSeek V4 Flash 0731 posts frontier-adjacent agent scores at $0.14/$0.28 (peak/off-peak pricing from Aug 16), GPT-5.6 Luna dropped 80% to $0.20/$1.20, and Gemini 3.5 Flash and Claude Haiku 4.5 hold the hosted middle. Prices verified July 31 and August 15, 2026.

Claude Mythos Preview is the model that found thousands of zero-days, and you could not buy it. Here is what it is, who got access through Project Glasswing, what it actually found, and where the model line went after it retired.

DeepSeek re-post-trained V4 Flash into an agent workhorse: Terminal Bench 82.7, DeepSWE 54.4, native Responses API, and first-party Codex support - all at $0.14/$0.28 per million tokens. What changed, what the numbers actually mean, and how to wire it up today.

DeepSeek shipped the official V4 Flash release on July 31, 2026. The re-post-trained 0731 build beats V4-Pro-Preview on agent benchmarks at $0.14/$0.28 per million tokens. Here is what changed and how to run it through OpenCode today.

Inkling-Small is a 276B-parameter MoE with 12B active per token, Apache 2.0, and open weights. It beats the 975B Inkling on SWEBench Verified (80.2), HLE (31.6), and tool use at a quarter of the size and a third of the output price.