Z.ai: GLM 5.3 Flash

Qwen3.7 Flash is the low-latency, cost-oriented tier of Alibaba's Qwen3.7 series, a vision-language reasoning model that accepts interleaved text and image input and returns text. It is built as a hybrid thinking model: like the rest of the Qwen3.7, Qwen3.6, and Qwen3.5 families served through Alibaba Cloud Model Studio, it can either emit an explicit reasoning trace before answering or respond directly, with thinking behavior controlled by an enable_thinking switch that defaults to on for the Qwen3.7 generation. The model exposes a context window of roughly one million tokens and a maximum generation length of 65,536 tokens, which allows long multi-image sequences, long documents, and extended agent trajectories to be held in a single request.Functionally, Qwen3.7 Flash targets multimodal agent workloads rather than pure chat. Reported strengths include object recognition, spatial understanding, and perception of real-world scenes, alongside visual coding, search, and computer-use style interaction where the model reads screen content and reasons over interface state. Weights are not published; the model is a proprietary endpoint positioned below Qwen3.7 Plus and Qwen3.7 Max in the same series, and it supports function calling and tool use for agentic pipelines.

Gemini 3.8 Flash is a natively multimodal reasoning model in Google's Gemini 3 series, positioned as the speed and cost oriented Flash tier while targeting long-horizon software engineering, autonomous agents, and enterprise workflows. It accepts text, images, video, audio, and PDF documents in a single request and returns text, with an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. Thinking is configurable at low, medium, and high levels, and the model supports function calling, code execution, structured outputs, context caching, search and Maps grounding, file search, and computer use in preview. Image generation, audio generation, and the Live API are not supported.On vision oriented evaluations the model reports 86.2% on CharXiv Reasoning for chart and figure synthesis and 87.8% on LVBench for long video understanding in agentic mode, alongside 90.8% on Terminal-Bench 2.1 and 61.6% on SWE-Bench Pro for coding. Following Gemini API conventions, it can localize objects by emitting bounding boxes as [ymin, xmin, ymax, xmax] integers normalized to a 0 to 1000 range, which supports prompt driven detection and grounding in addition to captioning, document parsing, and visual question answering. The knowledge cutoff is March 2026, though coverage in some domains reflects the January 2025 cutoff shared across the Gemini 3 family.

Gemini 3.7 Flash is a proprietary multimodal model from Google, positioned in the Flash branch of the Gemini 3 series that trades some of the capacity of the larger Pro models for lower latency and lower cost per token. It accepts interleaved text and image input alongside other modalities handled by the Gemini family and returns text, and it continues the series pattern of exposing a configurable thinking budget so that reasoning effort can be scaled up for harder problems or reduced for high throughput extraction, routing and classification work. The model is announced roughly three weeks after Gemini 3.6 Flash, part of an unusually fast iteration cadence within the Flash line.Google reports gains concentrated in agentic coding and front end generation, citing a WebDev Arena Elo of 1588 for this release compared with 1538 for the preceding Flash model, and describes it as producing more functional layouts and more feature complete applications in fewer prompts. Weights are not published and the architecture, parameter count and training corpus are undisclosed, consistent with prior Gemini releases. Visual capability follows the Flash lineage, covering image and document understanding, chart and diagram interpretation, text recognition in images, and general visual question answering.

GPT-5.6 Terra is the mid-tier reasoning model in OpenAI's GPT-5.6 family, which also includes the flagship Sol and the lightweight Luna. Introduced in a limited preview on June 26, 2026, and made broadly available on July 9, 2026, Terra accepts text and image input and produces text output, supporting vision, function calling, tool use, and agentic workflows. It is designed as a balanced option for everyday professional and production workloads — including coding assistance, document analysis, customer support, and multi-step agent tasks — where both output quality and cost efficiency matter. OpenAI positions Terra as delivering performance competitive with GPT-5.5 at approximately half the price, with a context window of around 1,050,000 tokens. On Terminal-Bench 2.1, Terra scores 84.3%, matching Claude Fable 5 on that benchmark. Under OpenAI's Preparedness Framework, Terra is rated High for cybersecurity and biological capabilities, meaning it demonstrates meaningful capability in those domains without reaching the Critical threshold.GPT-5.6 introduces a new naming convention in which the generation number (5.6) is paired with a durable capability tier name (Sol, Terra, or Luna), allowing each tier to advance on its own schedule. Terra carries the API identifier gpt-5.6-terra and supports the same reasoning effort controls available across the family, including adjustable reasoning depth. The model includes prompt caching with explicit cache breakpoints and a 30-minute minimum cache life, with cache writes billed at 1.25x the uncached input rate and cache reads receiving a 90% discount. GPT-5.6 Terra is a proprietary, closed-weights model served through the OpenAI API, Codex, and ChatGPT.

Claude Sonnet 5 is a mid-tier large language model from Anthropic, released on June 30, 2026, as the latest model in the Sonnet series and a direct successor to Claude Sonnet 4.6. It is a hybrid reasoning model designed primarily for agentic workflows, software coding, and professional tasks. The model features a 1 million token context window, a 128k maximum output token limit, and runs adaptive thinking by default, giving API users fine-grained control over reasoning effort across five levels (low, medium, high, max, and extra-high). It uses an updated tokenizer shared with Opus 4.7 and later models, which produces approximately 30% more tokens for equivalent text compared to earlier Claude models. On benchmarks, Sonnet 5 scores 63.2% on agentic coding and 81.2% on OSWorld, narrowing the gap with Opus 4.8 while remaining at Sonnet-tier pricing.The model supports text and image input with text output, and accepts tools including browsers and terminals for autonomous multi-step task execution. Anthropic's safety evaluations report that Sonnet 5 shows a lower rate of undesirable behaviors than Sonnet 4.6 and is generally safer in agentic contexts, with improved resistance to prompt injection and reduced sycophancy. Cybersecurity safeguards equivalent to those on Opus 4.7 and 4.8 are active, though Anthropic notes the model was not deliberately trained on cybersecurity tasks. The model is proprietary and API-only, with no open weights.

GLM-5V-Turbo is a native multimodal model from Z.ai that extends the GLM family with joint image, video, and text input aimed at vision-centered coding and agent workflows. The model reads screenshots, design drafts, document layouts, and interface captures and generates runnable code from them, covering tasks such as turning a visual design into a working front end, diagnosing rendering and layout defects from screen captures, and operating graphical user interfaces during long-horizon agent runs. It accepts roughly 200,000 input tokens and can emit up to 131,072 output tokens in a single response, which supports sessions that hold specifications, source files, logs, and visual references at the same time.Training includes a joint reinforcement learning stage spanning more than 30 tasks simultaneously, an approach Z.ai describes as a way to counter the trade-off in which improving visual recognition degrades programming ability and the reverse. Reported evaluations cover pure-text coding on the backend, frontend, and repository exploration tracks of CC-Bench-V2, together with agent execution suites such as PinchBench, ClawEval, and ZClawBench, indicating that text coding behavior is retained after visual input is added.