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
Muse Spark 1.2 compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Muse Spark 1.2MetaThis model | Muse Glimmer 30BMetaRemove | |
|---|---|---|
| Provider | Meta | Meta |
| Discovery tier | Frontier | Open weights |
| Added | Aug 5, 2026 | Aug 11, 2026 |
| Limits | ||
| Context window | 1MBest | 131.07K |
| Max output | 65.54K | — |
| Average output | 172 tokens | 682 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $1.25 | $0.35Best |
| Output | $4.25 | $1.50Best |
| Cache read | $0.15 | $0.04Best |
| Performance | ||
| Throughput | — | 69.2 tok/s |
| Time to first token | — | 0.9 s |
| Request success (24h) | — | 100.0% |
| Benchmark indexes | ||
| Intelligence Index | 39.6Best | 17.5 |
| Coding Index | 72.2Best | 49.0 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Vision | Yes | Yes |
| Structured output | Yes | Yes |
| PDF input | Yes | No |
| Audio input | Yes | No |
| Video input | Yes | No |
| Parallel tools | Yes | No |
| Reasoning effort | minimal, low, medium, high, xhigh | minimal, low, medium, high, xhigh |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Muse Spark 1.2
- Muse Glimmer 30B
Intelligence Index
- Muse Spark 1.239.6
- Muse Glimmer 30B17.5
Muse Spark 1.2 tested at xhigh reasoning effort
Muse Spark 1.2: Better than 84% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- Muse Spark 1.2: 72.2Top
- Muse Glimmer 30B: 49.0
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Muse Spark 1.2: 40.6%Top
- Muse Glimmer 30B: 6.8%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Muse Spark 1.2: 15.7%Top
- Muse Glimmer 30B: 0.8%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Muse Spark 1.2: 1,327 EloTop
- Muse Glimmer 30B: 477 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Muse Spark 1.2: 1,475 EloTop
- Muse Glimmer 30B: 783 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Muse Spark 1.2: 17.4%Top
- Muse Glimmer 30B: 10.0%
AA-LCRv1.1
Reasoning across long documents
- Muse Spark 1.2: 79.0%
- Muse Glimmer 30B: 83.3%Top
MLCR-AA
Long-context reasoning over medical records
- Muse Spark 1.2: 7.2%
- Muse Glimmer 30B: —
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Muse Spark 1.2: 45.5%Top
- Muse Glimmer 30B: 22.0%
GPQA Diamond
Graduate-level science questions
- Muse Spark 1.2: 90.4%Top
- Muse Glimmer 30B: 83.5%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Muse Spark 1.2: 7.1%Top
- Muse Glimmer 30B: 0.5%
SciCode
Scientific computing in Python
- Muse Spark 1.2: 57.4%Top
- Muse Glimmer 30B: 44.9%
Legacy evaluations
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Muse Spark 1.2: 79.0%
- Muse Glimmer 30B: 83.3%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
- Muse Spark 1.2
- Muse Glimmer 30B
| Leaderboard | Muse Spark 1.2 | Muse Glimmer 30B |
|---|---|---|
| Coding | #17 · 16.8% | Not in top 20 |
Ranks among Noumen catalog models on Use cases leaderboards. Only top-20 placements are listed.
- Muse Spark 1.2
- Muse Glimmer 30B
| Leaderboard | Muse Spark 1.2 | Muse Glimmer 30B |
|---|---|---|
| Overall | #10 · 1491.4 | Not in top 20 |
| Coding | #8 · 1541.3 | Not in top 20 |
| Hard Prompts | #13 · 1511.5 | Not in top 20 |
| English | #13 · 1492.1 | Not in top 20 |
| Exclude Ties | #10 · 1507.0 | Not in top 20 |
| French | #10 · 1511.4 | Not in top 20 |
| Hard Prompts English | #17 · 1509.2 | Not in top 20 |
| Industry Business And Management And Financial Operations | #3 · 1502.1 | Not in top 20 |
| Industry Legal And Government | #1 · 1522.7 | Not in top 20 |
| Industry Life And Physical And Social Science | #14 · 1508.6 | Not in top 20 |
| Industry Medicine And Healthcare | #9 · 1512.4 | Not in top 20 |
| Industry Software And It Services | #7 · 1532.2 | Not in top 20 |
| Korean | #9 · 1464.8 | Not in top 20 |
| Multi Turn | #6 · 1511.2 | Not in top 20 |
| Non English | #11 · 1483.8 | Not in top 20 |
| Russian | #17 · 1493.1 | Not in top 20 |
| Spanish | #11 · 1484.2 | Not in top 20 |
| Vision Style Control Overall | #7 · 1292.7 | Not in top 20 |
| Vision Style Control · Diagram | #16 · 1316.5 | Not in top 20 |
| Vision Style Control · Ocr | #7 · 1306.6 | Not in top 20 |
Ranks among Noumen catalog models on LMArena leaderboards. Only top-20 placements are listed.LMArena
- Muse Spark 1.2
- Muse Glimmer 30B
| Leaderboard | Muse Spark 1.2 | Muse Glimmer 30B |
|---|---|---|
| Creative Writing v3 | #19 · 1842 | Not in top 20 |
| Longform Writing | #13 · 81.5 | Not in top 20 |
Ranks among Noumen catalog models on EQ-Bench leaderboards. Only top-20 placements are listed.EQ-Bench
- Muse Spark 1.2
- Muse Glimmer 30B
| Leaderboard | Muse Spark 1.2 | Muse Glimmer 30B |
|---|---|---|
| Game Development | #20 · 1302 | Not in top 20 |
| Website | #12 · 1312 | Not in top 20 |
| UI Component | #17 · 1295 | Not in top 20 |
| Data Visualization | #7 · 1334 | Not in top 20 |
| SVG | #14 · 1281 | Not in top 20 |
| 3D | #19 · 1298 | Not in top 20 |
| ASCII Art | #6 · 1278 | Not in top 20 |
| Agentic Game Dev | #13 · 1141 | Not in top 20 |
| Web Apps | #17 · 1221 | Not in top 20 |
| Full Stack | #15 · 1210 | Not in top 20 |
| Native Apps | #8 · 1224 | Not in top 20 |
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.