Muse Spark 1.1

Tool callingStructured outputReasoningImage inputVideo inputFile input

Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.

Context: 1.0M
Released: 6mo ago
Input / 1M tokens: $1.25
Output / 1M tokens: $4.25
Cached input / 1M tokens: $0.15

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Other published benchmarks

Evaluation	Reported score and source
SimpleQA Verified	57.8% Epoch AI · muse-spark-1.1 Epoch AI evaluation

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer: Meta
Model family: Muse
Type: Language model
Predecessor: —
Successor: —
Released: April 8, 2026
Model ID: meta/muse-spark-1.1
Openness: Closed
License: —
Input modalities: text, image, video, file
Output modalities: text
Modality: text+image+file+video->text
Tokenizer: Other
Max output tokens: 944K
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: meta/muse-spark-1.1
Source family: muse
Last updated: 2026-07-09
Model context: 1.0M
Model output limit: 131K
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature control: Yes

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
SWE-Bench Pro	61.5 · resolve rate	2026-07-09	Source
Terminal-Bench	80 · success rate	2.1 · 2026-07-09	Source
DeepSWE	53.3 · resolve rate	1.1 · 2026-07-09	Source
MCP Atlas	88.1 · success rate	2026-07-09	Source
JobBench	54.7 · success rate	2026-07-09	Source
Toolathlon-Verified	75.6 · success rate	2026-07-09	Source
Humanity's Last Exam	62.1 · accuracy	with tools · 2026-07-09	Source
OSWorld-Verified	80.8 · success rate	2026-07-09	Source
Finance Agent	57.2 · accuracy	v2 · 2026-07-09	Source
CharXiv Reasoning	88.4 · accuracy	2026-07-09	Source
BabyVision	76.3 · accuracy	2026-07-09	Source

Complete source record (JSON)

{
  "id": "meta/muse-spark-1.1",
  "name": "Muse Spark 1.1",
  "description": "Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.",
  "family": "muse",
  "last_updated": "2026-07-09",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "pdf",
      "video"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 1048576,
    "output": 131072
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Pro",
      "score": 61.5,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "resolve rate",
      "date": "2026-07-09"
    },
    {
      "name": "Terminal-Bench",
      "score": 80,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "success rate",
      "version": "2.1",
      "date": "2026-07-09"
    },
    {
      "name": "DeepSWE",
      "score": 53.3,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "resolve rate",
      "version": "1.1",
      "date": "2026-07-09"
    },
    {
      "name": "MCP Atlas",
      "score": 88.1,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "success rate",
      "date": "2026-07-09"
    },
    {
      "name": "JobBench",
      "score": 54.7,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "success rate",
      "date": "2026-07-09"
    },
    {
      "name": "Toolathlon-Verified",
      "score": 75.6,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "success rate",
      "date": "2026-07-09"
    },
    {
      "name": "Humanity's Last Exam",
      "score": 62.1,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "accuracy",
      "variant": "with tools",
      "date": "2026-07-09"
    },
    {
      "name": "OSWorld-Verified",
      "score": 80.8,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "success rate",
      "date": "2026-07-09"
    },
    {
      "name": "Finance Agent",
      "score": 57.2,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "accuracy",
      "version": "v2",
      "date": "2026-07-09"
    },
    {
      "name": "CharXiv Reasoning",
      "score": 88.4,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "accuracy",
      "date": "2026-07-09"
    },
    {
      "name": "BabyVision",
      "score": 76.3,
      "source": "https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/",
      "metric": "accuracy",
      "date": "2026-07-09"
    }
  ],
  "release_date": "2026-04-08",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Meta	meta	1.0M	$1.25	$4.25	$0.15	—	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter