NOUMENOpen app
NOUMEN

Meta · Open weights

Llama 4 Scout

Added Sep 5, 2025Open weights

Compare models

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

Loading models…

Use in the app

Llama 4 Scout, a 17 billion active parameter model with 16 experts, is the best multimodal model in the world in its class and is more powerful than all previous generation Llama models, while fitting in a single H100 GPU. Additionally, Llama 4 Scout offers an industry-leading context window of 10M and delivers better results than Gemma 3, Gemini 2.0 Flash-Lite, and Mistral 3.1 across a broad range of widely reported benchmarks.

  • Tools
  • Vision
  • Structured output
Input
Text, Images
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.085
Output
$0.46

Reference prices as published by the model provider. API example

Specifications

Context window
328K
Max output
65.5K
Average output (7 days)
79 tokens
Longer than 7% of 465 models

Side by side

Llama 4 Scout 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…

Llama 4 ScoutMetaThis modelMuse Glimmer 30BMetaRemove
ProviderMetaMeta
Discovery tierOpen weightsOpen weights
AddedSep 5, 2025Aug 11, 2026
Limits
Context window328KBest131.07K
Max output65.54K—
Average output79 tokens682 tokens
Pricing, USD per 1M tokens
Input$0.085Best$0.35
Output$0.46Best$1.50
Cache read—$0.04
Performance
Throughput—70.8 tok/s
Time to first token—1.1 s
Request success (24h)91.6%100.0%Best
Benchmark indexes
Intelligence Index6.517.5Best
Coding Index8.249.0Best
Math Index14.0—
Capabilities
ReasoningNoYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
Reasoning effort—minimal, low, medium, high, xhigh

Public evaluations

Benchmarks

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

  • Llama 4 Scout
  • Muse Glimmer 30B

Intelligence Index

  • Llama 4 Scout6.5
  • Muse Glimmer 30B17.5

Llama 4 Scout: Better than 5% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Llama 4 Scout: 8.2
    • Muse Glimmer 30B: 49.0Top

  • Math Index

    Composite of the math evaluations

    • Llama 4 Scout: 14.0
    • Muse Glimmer 30B: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Llama 4 Scout: 0.2%
    • Muse Glimmer 30B: 6.8%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Llama 4 Scout: 0.0%
    • Muse Glimmer 30B: 0.8%Top

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Llama 4 Scout: —
    • Muse Glimmer 30B: 477 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Llama 4 Scout: —
    • Muse Glimmer 30B: 783 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Llama 4 Scout: 0.0%
    • Muse Glimmer 30B: 10.0%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Llama 4 Scout: 27.7%
    • Muse Glimmer 30B: 83.3%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Llama 4 Scout: 3.8%
    • Muse Glimmer 30B: 22.0%Top

  • GPQA Diamond

    Graduate-level science questions

    • Llama 4 Scout: 58.7%
    • Muse Glimmer 30B: 83.5%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Llama 4 Scout: 75.2%
    • Muse Glimmer 30B: —

  • IFBench

    Following precise output instructions

    • Llama 4 Scout: 39.5%
    • Muse Glimmer 30B: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Llama 4 Scout: 0.0%
    • Muse Glimmer 30B: 0.5%Top

  • SciCode

    Scientific computing in Python

    • Llama 4 Scout: 21.3%
    • Muse Glimmer 30B: 44.9%Top

  • LiveCodeBench

    Recent competitive programming problems

    • Llama 4 Scout: 29.9%
    • Muse Glimmer 30B: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Llama 4 Scout: 14.0%
    • Muse Glimmer 30B: —

  • AIME

    Competition mathematics

    • Llama 4 Scout: 28.3%
    • Muse Glimmer 30B: —

  • MATH-500

    Competition math problems

    • Llama 4 Scout: 84.4%
    • Muse Glimmer 30B: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Llama 4 Scout: 1.5%
    • Muse Glimmer 30B: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Llama 4 Scout: 15.5%
    • Muse Glimmer 30B: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Llama 4 Scout: 27.7%
    • Muse Glimmer 30B: 83.3%Top

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
0.0%
Request success (24h)
91.6%

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.

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-llama/llama-4-scout",
    "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-scout",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Meta

Other Meta models, starting with the same family.