5 models
Ranked by DeepSWE
Reasoning Tools JSON 78.8

Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.

meta/muse-wonder-1.0 2026-10-12 1.04858M context $4/M input $20/M output
11 providers
Reasoning Tools JSON 75.4

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...

meta/muse-spark-1.3 2026-09-02 1.04858M context $1.25/M input $4.25/M output
16 providers
Reasoning Tools Open weights 60.0

Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...

meta/muse-spark-open 2026-10-15 1.04858M context $1.25/M input $4.25/M output
14 providers
Reasoning Tools JSON 59.3

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....

meta/muse-spark-1.2 2026-08-05 1.04858M context $1.25/M input $4.25/M output
18 providers
Reasoning Tools JSON 53.3

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....

meta/muse-spark-1.1 2026-04-08 1.04858M context $1.25/M input $4.25/M output
17 providers