Meta · Frontier
Muse Wonder
Meta's Muse Wonder is a frontier reasoning model designed for complex personal and professional agentic tasks. It accepts text, images, audio, video, and PDF documents across a one-million-token context window, supports tool calling and structured output, and always reasons before answering.
- Reasoning
- Tools
- Vision
- Structured output
- PDF input
- Audio input
- Video input
- Input
- Text, Images, Video, Audio
- Output
- Text
- Reasoning effort
- minimal · low · medium · high · xhigh · max
- Discovery tier
- Frontier
Pricing
USD per 1M tokens- Input
- $4.00
- Output
- $20.00
- Cache read
- $0.20
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- —
- Average output (7 days)
- 1.2K tokens
- Longer than 77% of 473 models
Side by side
Compare models
Put Muse Wonder 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
52.4
Tested at max reasoning effort
Better than 97% of 326 scored models
Agentic work
AutomationBench-AA
68.1%Workflow automation, penalized for guardrail violations
Better than 96% of 173 scored models
AutomationBench-AA tasks completed
39.1%Workflows finished end to end without a guardrail violation
Better than 97% of 173 scored models
Harvey LAB-AAv1.1
10.0%Legal tasks passed in full, with no material hallucination
Highest of 29 scored models
AA-Briefcasev1.1
1,659 EloAgentic knowledge work, rated head to head
Better than 95% of 166 scored models
GDPval-AAv2.1
1,770 EloEconomically valuable occupational tasks, rated head to head
Better than 98% of 187 scored models
Document reasoning
GDP.pdf
30.6%Professional reasoning over PDF documents, all-pass rate
Better than 98% of 171 scored models
AA-LCRv1.1
80.7%Reasoning across long documents
Better than 83% of 309 scored models
MLCR-AA
22.2%Long-context reasoning over medical records
Better than 85% of 121 scored models
Reasoning and knowledge
Humanity’s Last Exam
50.1%Expert-level questions across academic fields
Better than 95% of 323 scored models
Coding
Terminal-Benchv4.0
52.0%Practical software engineering in a terminal
Better than 95% of 171 scored models
SciCode
60.3%Scientific computing in Python
Better than 93% of 174 scored models
Legacy evaluations
AA-LCR (unversioned)
80.7%Long-context reasoning, earlier grading
Better than 83% of 309 scored models
Scores from Artificial Analysis, updated Oct 26, 2026. Muse Wonder was tested at max reasoning effort; compare scores measured at the same effort.Artificial Analysis
- #3Combined33.2%
Ranks among Noumen catalog models on Combined leaderboards. Only top-20 placements are listed.
- #5Roleplay51.4%
- #8Creative writing40.0%
- #12Coding21.2%
Ranks among Noumen catalog models on Use cases leaderboards. Only top-20 placements are listed.
- #3Overall1508.7
- #6Coding1544.7
- #11Longer Query1501.6
- #5Creative Writing1492.0
- #7Instruction Following1497.5
- #7Hard Prompts1521.9
- #8Chinese1543.7
- #3English1515.7
- #2Exclude Ties1533.0
- #15Expert1525.8
- #2French1530.4
- #6Hard Prompts English1523.3
- #7Industry Business And Management And Financial Operations1497.8
- #5Industry Entertainment And Sports And Media1484.9
- #3Industry Legal And Government1510.6
- #7Industry Life And Physical And Social Science1521.3
- #6Industry Mathematical1519.5
- #3Industry Medicine And Healthcare1524.2
- #6Industry Software And It Services1533.5
- #4Industry Writing And Literature And Language1500.5
- #2Multi Turn1519.3
- #2Non English1498.3
- #1Russian1532.5
- #12Spanish1483.6
- #12WebDev Overall1651.0
- #12WebDev · Webdev1651.0
- #6WebDev · Webdev-html1684.2
- #15WebDev · Webdev-react1645.3
Ranks among Noumen catalog models on LMArena leaderboards. Only top-20 placements are listed.LMArena
- #12Epoch Capabilities Index161.8
Ranks among Noumen catalog models on Epoch AI leaderboards. Only top-20 placements are listed.Epoch AI
- #3EQ-Bench 41324
- #9Creative Writing v32007
Ranks among Noumen catalog models on EQ-Bench leaderboards. Only top-20 placements are listed.EQ-Bench
- #5Game Development1405
- #1Website1368
- #4UI Component1374
- #13Data Visualization1307
- #43D1446
Ranks among Noumen catalog models on Design Arena leaderboards. Only top-20 placements are listed.Design Arena
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Throughput
- 113.8 tok/s
- Faster than 67% of 259 models
- Time to first token
- 1.8 s
- Quicker than 78% of 259 models
- Prompt cache hits
- 37.3%
- About $2.58 per 1M input tokens with caching
- Request success (24h)
- 99.5%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
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-wonder",
"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-wonder",
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.