The Vision AI Playground: test and compare models on your own images

Claude Opus 5.5 is a proprietary multimodal reasoning model from Anthropic and the first entry in the Claude 5.5 family. It accepts interleaved text and image input and returns text, with a one million token context window and up to 128,000 output tokens per response. Adaptive thinking is always enabled on this model and cannot be disabled; thinking depth is instead governed by an effort parameter with five levels, where medium is the default, a change from the high default used by Claude Opus 5 and earlier Opus models. Anthropic reports a knowledge cutoff of June 2026.On the visual side, Anthropic characterizes Opus 5.5 as its strongest Opus release for vision and computer use, describing improved reading of dense documents, charts, screenshots, and diagrams for document extraction and visual analysis tasks. Published results include 89.0% on Chartography with tools and 81.8% on OSWorld 2.0 under partial credit scoring, alongside 48.7% under strict scoring reported in the system card. The accompanying system card states that Opus 5.5 scored higher than Opus 5 on every evaluation in its capability summary, with the largest gains concentrated in agentic coding, visual reasoning, computer use, and long-horizon knowledge work. The model ships with safety classifiers covering biology and cybersecurity that can route blocked requests to earlier Claude models.

GPT-6 Luna is the fast, cost-efficient tier of OpenAI's GPT-6 model family, sitting below GPT-6 Sol and the larger GPT-6 Astra model that opened the generation. It is a proprietary multimodal transformer that accepts text and image input and returns text, and it exposes an adjustable reasoning effort setting so the same model can run in a low-latency mode or spend additional inference compute on harder problems. OpenAI positions it for high-volume and latency-sensitive workloads such as conversational assistants, classification, and lightweight agentic pipelines, while noting that at higher reasoning effort it handles software engineering and computer-use tasks that previously required a Sol-tier model.The model supports a context window of roughly 1,050,000 input tokens with a maximum output of 128,000 tokens, which allows long documents, extended agent traces, and large code repositories to be processed in a single request. OpenAI describes the GPT-6 generation as improving factual reliability and adopting a more concise communication style relative to the GPT-5.6 series, and attributes the efficiency of the Sol and Luna tiers to gains in caching and inference rather than to reduced capability. Architecture details, parameter counts, and training data are not published.

GPT-6 Sol is a proprietary multimodal reasoning model from OpenAI, released on September 22, 2026 alongside GPT-6 Luna as an efficiency-oriented tier of the GPT-6 family that began with GPT-6 Astra. OpenAI states that Sol and Luna are trained with methods similar to those used for Astra, carrying the same work on professional tasks, factuality, coding, computer use, and alignment into models that run faster. Sol accepts text and image input and returns text output, and OpenAI documents a context window of roughly one million tokens together with a knowledge cutoff of April 20, 2026.The model targets complex coding and agentic workflows and exposes a configurable reasoning effort setting with levels of none, low, medium, high, xhigh, and max, which trades latency and token consumption against answer quality. OpenAI reports results including 33.2% on AutomationBench at xhigh effort and 56.4% on Agents' Last Exam at max effort, while its reported DeepSWE and OSWorld 2.0 figures of 68.8% and 64.4% fall below those of the earlier GPT-5.6 Sol. Its vision behavior covers image understanding tasks such as visual question answering, captioning, document and chart interpretation, and text recognition.

MiMo-V2.6-Flash is the efficiency-oriented checkpoint of Xiaomi's MiMo-V2.6 series, a natively omnimodal foundation model that accepts text, image, video, and audio in a single model and supports a one million token context window. The language backbone is a sparse mixture-of-experts transformer with roughly 309 billion total parameters and 15 billion activated per token, organized as 48 layers with 256 routed experts and top-8 routing. It uses a hybrid attention scheme that interleaves sliding window attention with global attention layers to cut key-value cache cost on long sequences, and pairs the backbone with a vision encoder, an audio encoder, and an audio tokenizer, plus a multi-token prediction module and a draft model for faster decoding.Training emphasizes large scale reinforcement learning on verifiable, long-horizon tasks, with RL compute, environment diversity, and grader compute scaled together in a single mixed run. Xiaomi reports gains during RL on SWE-bench Verified, Terminal Bench, a cybersecurity benchmark, and an internal visual coding benchmark, reflecting a focus on agentic coding, computer use, and multimodal document and screen understanding rather than single turn chat.

MiMo V2.6 Pro is the flagship omni-modal foundation model in Xiaomi's MiMo V2.6 series, released as open weights alongside a Flash variant and a 9B distillation of Qwen3.5. It uses a sparse mixture-of-experts transformer with 1.02 trillion total parameters and roughly 42 billion activated per token, paired with a hybrid attention design that interleaves sliding-window and global attention layers to support a context window of about one million tokens. Dedicated encoders handle non-text inputs, including a vision encoder of roughly 681 million parameters and an audio tokenizer stack, so the model accepts text, images, video, and audio and returns text.Post-training centers on large-scale reinforcement learning across thousands of interactive environments, combined with agentic grading, self-correction cold start, and a multi-prefix multi-teacher on-policy distillation stage that extends behavior to tasks that are hard to verify automatically. The resulting model targets long-horizon agentic work such as software engineering, terminal and computer-use operation, tool calling, cybersecurity analysis, and visual coding, and it reports gains over the prior MiMo generation on SWE-bench Verified, Terminal Bench, and internal visual coding and cyber benchmarks.

Grok 4.7 is a proprietary multimodal reasoning model from SpaceXAI that accepts images alongside text and returns text-only output. On visual inputs it supports image captioning, visual question answering, OCR, document and chart question answering, and image classification and tagging, with all results expressed as generated text rather than bounding boxes or masks. Its 500,000 token context window leaves room for several images, long documents, or extended conversations about visual content in a single request.The model exposes a configurable reasoning effort setting with low, medium, high, and xhigh levels (high by default), letting callers trade latency for the amount of deliberation spent on a prompt, including multi-step questions about an image. Built on a larger base model than Grok 4.6 with extended reinforcement learning on harder tasks, it works longer on difficult problems and checks its own work more carefully at the same serving speed. SpaceXAI's launch materials focus on coding and agentic knowledge work and report no image benchmark results.