Meta · Open weights
Llama 4 Maverick
Llama 4 Maverick, a 17 billion active parameter model with 128 experts, is the best multimodal model in its class, beating GPT-4o and Gemini 2.0 Flash across a broad range of widely reported benchmarks, while achieving comparable results to the new DeepSeek v3 on reasoning and coding—at less than half the active parameters. Llama 4 Maverick offers a best-in-class performance to cost ratio with an experimental chat version scoring ELO of 1417 on LMArena.
- Tools
- Vision
- Structured output
- Input
- Text, Images
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.19
- Output
- $0.65
- Cache read
- $0.05
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- 65.5K
- Average output (7 days)
- 114 tokens
- Longer than 11% of 465 models
Side by side
Llama 4 Maverick compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Llama 4 MaverickMetaThis model | Qwen3 Coder NextQwenRemove | |
|---|---|---|
| Provider | Meta | Qwen |
| Discovery tier | Open weights | Open weights |
| Added | Sep 5, 2025 | Dec 8, 2025 |
| Limits | ||
| Context window | 1.05MBest | 262.14K |
| Max output | 65.54K | 65.54K |
| Average output | 114 tokens | 182 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.19Best | $0.25 |
| Output | $0.65Best | $0.80 |
| Cache read | $0.05Best | $0.0798 |
| Performance | ||
| Throughput | — | 119.9 tok/s |
| Time to first token | — | 1.6 s |
| Request success (24h) | 99.6%Best | 92.1% |
| Benchmark indexes | ||
| Intelligence Index | 9.3Best | 9.2 |
| Coding Index | 16.3 | 36.2Best |
| Math Index | 19.3 | — |
| Capabilities | ||
| Tools | Yes | Yes |
| Vision | Yes | No |
| Structured output | Yes | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Llama 4 Maverick
- Qwen3 Coder Next
Intelligence Index
- Llama 4 Maverick9.3
- Qwen3 Coder Next9.2
Llama 4 Maverick: Better than 18% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- Llama 4 Maverick: 16.3
- Qwen3 Coder Next: 36.2Top
Math Index
Composite of the math evaluations
- Llama 4 Maverick: 19.3
- Qwen3 Coder Next: —
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Llama 4 Maverick: 0.2%
- Qwen3 Coder Next: 1.1%Top
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Llama 4 Maverick: 0.0%Top
- Qwen3 Coder Next: 0.0%Top
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Llama 4 Maverick: —
- Qwen3 Coder Next: 404 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Llama 4 Maverick: —
- Qwen3 Coder Next: 513 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Llama 4 Maverick: 0.8%
- Qwen3 Coder Next: 2.6%Top
AA-LCRv1.1
Reasoning across long documents
- Llama 4 Maverick: 50.0%Top
- Qwen3 Coder Next: 47.0%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Llama 4 Maverick: 4.9%
- Qwen3 Coder Next: 10.1%Top
GPQA Diamond
Graduate-level science questions
- Llama 4 Maverick: 67.1%
- Qwen3 Coder Next: 73.7%Top
MMLU-Pro
Multi-subject knowledge and reasoning
- Llama 4 Maverick: 80.9%
- Qwen3 Coder Next: —
IFBench
Following precise output instructions
- Llama 4 Maverick: 43.0%Top
- Qwen3 Coder Next: 35.2%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Llama 4 Maverick: 0.0%Top
- Qwen3 Coder Next: 0.0%Top
SciCode
Scientific computing in Python
- Llama 4 Maverick: 31.7%
- Qwen3 Coder Next: 36.2%Top
LiveCodeBench
Recent competitive programming problems
- Llama 4 Maverick: 39.7%
- Qwen3 Coder Next: —
Math
AIME 2025
Competition mathematics, 2025 problems
- Llama 4 Maverick: 19.3%
- Qwen3 Coder Next: —
AIME
Competition mathematics
- Llama 4 Maverick: 39.0%
- Qwen3 Coder Next: —
MATH-500
Competition math problems
- Llama 4 Maverick: 88.9%
- Qwen3 Coder Next: —
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Llama 4 Maverick: 6.8%
- Qwen3 Coder Next: 18.2%Top
τ²-Bench Telecom
Tool use in a customer-support simulation
- Llama 4 Maverick: 17.8%
- Qwen3 Coder Next: 79.5%Top
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Llama 4 Maverick: 50.0%Top
- Qwen3 Coder Next: 47.0%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
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.
- Prompt cache hits
- 6.8%
- About $0.18 per 1M input tokens with caching
- Request success (24h)
- 99.6%
- 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-llama/llama-4-maverick",
"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-llama/llama-4-maverick",
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.