NOUMENOpen app
NOUMEN

Meta · Frontier

Muse Spark 1.2

Added Aug 5, 2026

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Meta's Muse Spark 1.2 is a multimodal reasoning model for complex agentic and coding tasks, with tool calling, structured output, and a one-million-token context window.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • PDF input
  • Audio input
  • Video input
  • Parallel tools
Input
Text, Images, Video, Audio
Output
Text
Reasoning effort
minimal · low · medium · high · xhigh
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$1.25
Output
$4.25
Cache read
$0.15

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K
Average output (7 days)
172 tokens
Longer than 17% of 473 models

Side by side

Muse Spark 1.2 compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Muse Spark 1.2MetaThis modelDeepSeek V4.1 Flash ThinkingDeepSeekRemove
ProviderMetaDeepSeek
Discovery tierFrontierOpen weights
AddedAug 5, 2026Sep 8, 2026
Limits
Context window1M1M
Max output65.54K384KBest
Average output172 tokens785 tokens
Pricing, USD per 1M tokens
Input$1.25$0.09Best
Output$4.25$0.25Best
Cache read$0.15$0.006Best
Performance
Throughput—227.2 tok/s
Time to first token—3.7 s
Request success (24h)—99.9%
Benchmark indexes
Intelligence Index39.6Best39.5
Coding Index72.2—
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesNo
Audio inputYesNo
Video inputYesNo
Parallel toolsYesNo
Reasoning effortminimal, low, medium, high, xhighnone, low, high, max

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Muse Spark 1.2
  • DeepSeek V4.1 Flash Thinking

Intelligence Index

  • Muse Spark 1.239.6
  • DeepSeek V4.1 Flash Thinking39.5

Muse Spark 1.2 tested at xhigh reasoning effort

Muse Spark 1.2: Better than 84% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Muse Spark 1.2: 72.2
    • DeepSeek V4.1 Flash Thinking: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Muse Spark 1.2: 40.6%
    • DeepSeek V4.1 Flash Thinking: 68.9%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Muse Spark 1.2: 15.7%
    • DeepSeek V4.1 Flash Thinking: 35.5%Top

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Muse Spark 1.2: —
    • DeepSeek V4.1 Flash Thinking: 1.7%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Muse Spark 1.2: 1,327 Elo
    • DeepSeek V4.1 Flash Thinking: 1,419 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Muse Spark 1.2: 1,475 Elo
    • DeepSeek V4.1 Flash Thinking: 1,600 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Muse Spark 1.2: 17.4%Top
    • DeepSeek V4.1 Flash Thinking: 12.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • Muse Spark 1.2: 79.0%
    • DeepSeek V4.1 Flash Thinking: 84.0%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Muse Spark 1.2: 7.2%
    • DeepSeek V4.1 Flash Thinking: 23.9%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Muse Spark 1.2: 45.5%Top
    • DeepSeek V4.1 Flash Thinking: 39.2%

  • GPQA Diamond

    Graduate-level science questions

    • Muse Spark 1.2: 90.4%
    • DeepSeek V4.1 Flash Thinking: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Muse Spark 1.2: 7.1%
    • DeepSeek V4.1 Flash Thinking: 26.8%Top

  • SciCode

    Scientific computing in Python

    • Muse Spark 1.2: 57.4%Top
    • DeepSeek V4.1 Flash Thinking: 51.9%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Muse Spark 1.2: 79.0%
    • DeepSeek V4.1 Flash Thinking: 84.0%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Muse Spark 1.2 was tested at xhigh reasoning effort; compare scores measured at the same effort.Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta/muse-spark-1.2",
    "reasoning_effort": "medium",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="meta/muse-spark-1.2",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Meta

Other Meta models, starting with the same family.