all the models — AI benchmark observatory
← Models

Muse Spark 1.1

Meta · proprietary · muse-spark-1.1

Muse Spark 1.1 is Meta Superintelligence Labs' multimodal reasoning model for agentic tasks. It improves tool and computer use, coding, and multimodal understanding over Muse Spark, can orchestrate parallel subagents, and actively manages a 1,048,576-token context window. The Meta Model API supports text, image, PDF, and video inputs, up to 131,072 output tokens, structured output, parallel tool calling, and built-in web search with citations.

CharXiv-RMCP AtlasOSWorld-VeriTerminal-BenToolathlonHumanity's L

Benchmark scores

Pricing

  • Meta Model API$1.25 / $4.25

Input / output per 1M tokens

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • vision1281
  • text1493
  • code1542