Meta · Frontier
Muse Spark 1.2
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
Compare models
Put Muse Spark 1.2 next to up to three other models. The comparison stays in the link, so you can share it.
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
Intelligence Index
39.6
Tested at xhigh reasoning effort
Better than 84% of 326 scored models
Indexes
Coding Index
72.2Composite of the coding evaluations
Better than 82% of 168 scored models
Agentic work
AutomationBench-AA
40.6%Workflow automation, penalized for guardrail violations
Better than 57% of 173 scored models
AutomationBench-AA tasks completed
15.7%Workflows finished end to end without a guardrail violation
Better than 61% of 173 scored models
AA-Briefcasev1.1
1,327 EloAgentic knowledge work, rated head to head
Better than 69% of 166 scored models
GDPval-AAv2.1
1,475 EloEconomically valuable occupational tasks, rated head to head
Better than 77% of 187 scored models
Document reasoning
GDP.pdf
17.4%Professional reasoning over PDF documents, all-pass rate
Better than 68% of 171 scored models
AA-LCRv1.1
79.0%Reasoning across long documents
Better than 72% of 309 scored models
MLCR-AA
7.2%Long-context reasoning over medical records
Better than 26% of 121 scored models
Reasoning and knowledge
Humanity’s Last Exam
45.5%Expert-level questions across academic fields
Better than 87% of 323 scored models
GPQA Diamond
90.4%Graduate-level science questions
Better than 79% of 291 scored models
Coding
Terminal-Benchv4.0
7.1%Practical software engineering in a terminal
Better than 58% of 171 scored models
SciCode
57.4%Scientific computing in Python
Better than 82% of 174 scored models
Legacy evaluations
AA-LCR (unversioned)
79.0%Long-context reasoning, earlier grading
Better than 72% of 309 scored models
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
- #17Coding16.8%
Ranks among Noumen catalog models on Use cases leaderboards. Only top-20 placements are listed.
- #10Overall1491.4
- #8Coding1541.3
- #13Hard Prompts1511.5
- #13English1492.1
- #10Exclude Ties1507.0
- #10French1511.4
- #17Hard Prompts English1509.2
- #3Industry Business And Management And Financial Operations1502.1
- #1Industry Legal And Government1522.7
- #14Industry Life And Physical And Social Science1508.6
- #9Industry Medicine And Healthcare1512.4
- #7Industry Software And It Services1532.2
- #9Korean1464.8
- #6Multi Turn1511.2
- #11Non English1483.8
- #17Russian1493.1
- #11Spanish1484.2
- #7Vision Style Control Overall1292.7
- #16Vision Style Control · Diagram1316.5
- #7Vision Style Control · Ocr1306.6
Ranks among Noumen catalog models on LMArena leaderboards. Only top-20 placements are listed.LMArena
- #19Creative Writing v31842
- #13Longform Writing81.5
Ranks among Noumen catalog models on EQ-Bench leaderboards. Only top-20 placements are listed.EQ-Bench
- #20Game Development1302
- #12Website1312
- #17UI Component1295
- #7Data Visualization1334
- #14SVG1281
- #193D1298
- #6ASCII Art1278
- #13Agentic Game Dev1141
- #17Web Apps1221
- #15Full Stack1210
- #8Native Apps1224
Ranks among Noumen catalog models on Design Arena leaderboards. Only top-20 placements are listed.Design Arena
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
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
Related models
Other Meta models, starting with the same family.