Vertical Tabs
Get Started
Meta

Muse Spark 1.2

Tool callingStructured outputReasoningImage inputAudio inputVideo inputFile input
Website

Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.

Context
1.0M
Released
2mo 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

EvaluationReported score and source
SimpleQA Verified
60.3%
Epoch AI · muse-spark-1.2_xhigh
Reasoning effort: xhigh
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
August 5, 2026
Model ID
meta/muse-spark-1.2
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-1.2
Source family
muse
Last updated
2026-08-05
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

BenchmarkScoreEvaluation detailsEvidence
GDPval-AA1615 · EloStirrup · xhigh effort · 2 · 2026-09-02Source
JobBench61.6 · mean rubric scoreOpenCode · xhigh effort · 2026-09-02Source
OSWorld47.6 · mean partial scoreMeta internal evaluation framework · 06.24 · xhigh effort · 2.0 · 2026-09-02Source
OSWorld17.9 · binary completion rateMeta internal evaluation framework · 06.24 · xhigh effort · 2.0 · 2026-09-02Source
DeepSearchQA85.9 · F1Meta browser harness · xhigh effort · 2026-09-02Source
Agentic IF Index46.2 · scoreMeta internal · xhigh effort · 2026-09-02Source
AutomationBench38.2 · pass@1public v3 task set · xhigh effort · 2026-09-02Source
MRCR66.3 · mean sequence-match ratio8-needle, 256K-512K · xhigh effort · 2 · 2026-09-02Source
MRCR55.5 · mean sequence-match ratio8-needle, 512K-1M · xhigh effort · 2 · 2026-09-02Source
DeepSWE55 · pass@1mini-swe-agent · xhigh effort · 1.1 · 2026-09-02Source
SWE-Atlas Codebase QnA46.2 · pass@1mini-swe-agent · xhigh effort · 2026-09-02Source
Terminal-Bench82.9 · pass@1Muse Code · xhigh effort · 2.1 · 2026-09-02Source
DeepSWE59.3 · pass@1Muse Code · xhigh effort · 1.1 · 2026-08-05Source
MCP Atlas90.3 · pass rateScale AI · xhigh effort · 2026-08-05Source
Complete source record (JSON)
{
  "id": "meta/muse-spark-1.2",
  "name": "Muse Spark 1.2",
  "description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
  "family": "muse",
  "last_updated": "2026-08-05",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "video",
      "pdf",
      "audio"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 1048576,
    "output": 131072
  },
  "benchmarks": [
    {
      "name": "GDPval-AA",
      "score": 1615,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "Elo",
      "harness": "Stirrup",
      "variant": "xhigh effort",
      "version": "2",
      "date": "2026-09-02"
    },
    {
      "name": "JobBench",
      "score": 61.6,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "mean rubric score",
      "harness": "OpenCode",
      "variant": "xhigh effort",
      "date": "2026-09-02"
    },
    {
      "name": "OSWorld",
      "score": 47.6,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "mean partial score",
      "harness": "Meta internal evaluation framework",
      "variant": "xhigh effort",
      "dataset": "06.24",
      "version": "2.0",
      "date": "2026-09-02"
    },
    {
      "name": "OSWorld",
      "score": 17.9,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "binary completion rate",
      "harness": "Meta internal evaluation framework",
      "variant": "xhigh effort",
      "dataset": "06.24",
      "version": "2.0",
      "date": "2026-09-02"
    },
    {
      "name": "DeepSearchQA",
      "score": 85.9,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "F1",
      "harness": "Meta browser harness",
      "variant": "xhigh effort",
      "date": "2026-09-02"
    },
    {
      "name": "Agentic IF Index",
      "score": 46.2,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "score",
      "variant": "xhigh effort",
      "dataset": "Meta internal",
      "date": "2026-09-02"
    },
    {
      "name": "AutomationBench",
      "score": 38.2,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "pass@1",
      "variant": "xhigh effort",
      "dataset": "public v3 task set",
      "date": "2026-09-02"
    },
    {
      "name": "MRCR",
      "score": 66.3,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "mean sequence-match ratio",
      "variant": "xhigh effort",
      "dataset": "8-needle, 256K-512K",
      "version": "2",
      "date": "2026-09-02"
    },
    {
      "name": "MRCR",
      "score": 55.5,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "mean sequence-match ratio",
      "variant": "xhigh effort",
      "dataset": "8-needle, 512K-1M",
      "version": "2",
      "date": "2026-09-02"
    },
    {
      "name": "DeepSWE",
      "score": 55,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "pass@1",
      "harness": "mini-swe-agent",
      "variant": "xhigh effort",
      "version": "1.1",
      "date": "2026-09-02"
    },
    {
      "name": "SWE-Atlas Codebase QnA",
      "score": 46.2,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "pass@1",
      "harness": "mini-swe-agent",
      "variant": "xhigh effort",
      "date": "2026-09-02"
    },
    {
      "name": "Terminal-Bench",
      "score": 82.9,
      "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "metric": "pass@1",
      "harness": "Muse Code",
      "variant": "xhigh effort",
      "version": "2.1",
      "date": "2026-09-02"
    },
    {
      "name": "DeepSWE",
      "score": 59.3,
      "source": "https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2",
      "metric": "pass@1",
      "harness": "Muse Code",
      "variant": "xhigh effort",
      "version": "1.1",
      "date": "2026-08-05"
    },
    {
      "name": "MCP Atlas",
      "score": 90.3,
      "source": "https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2",
      "metric": "pass rate",
      "harness": "Scale AI",
      "variant": "xhigh effort",
      "date": "2026-08-05"
    }
  ],
  "release_date": "2026-08-05",
  "open_weights": false
}

Infrastructure

Provider availability

All providers
ProviderEndpointContextInput /M tokensOutput /M tokensCached input /M tokensCache write /M tokensUptime 1dData handling
Metameta1.0M$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