Claude Opus 5.5 vs Muse Spark 1.2

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.

Muse Spark 1.2 is a proprietary multimodal reasoning model from Meta Superintelligence Labs, released as a coding-focused update to Muse Spark 1.1. It accepts text, images, video, audio, and PDF documents and returns text, with a context window of roughly one million tokens that allows whole repositories, long documents, and extended agent trajectories to be held in a single request. The model thinks before answering, and the amount of reasoning effort it spends is configurable per request. Alongside its visual and document understanding, it supports structured output and parallel function calling, and it is designed to operate either as a planning agent that delegates work or as a subagent executing tasks in parallel.

Training for version 1.2 scaled up compute on coding tasks and widened the diversity of training environments, concentrating on long-horizon work such as whole-repository generation, large end-to-end projects, and automated research. Part of the training data was self-generated, with Muse Spark 1.1 producing coding environments and instruction-following templates and grading candidate solutions against them. The model was co-trained with the Muse Code terminal agent, incorporating rejection-sampled harness trajectories and that toolset. Meta reports 82.9 percent on Terminal-Bench 2.1, an improvement of 6.7 points over Muse Spark 1.1. Multimodal use cases documented for the family include visual-to-code generation and detailed image and video captioning.