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 modelQwen3 30B A3BQwenRemove
ProviderMetaQwen
Discovery tierOpen weightsOpen weights
AddedSep 5, 2025Feb 27, 2025
Limits
Context window328KBest41K
Max output65.54KBest32.77K
Average output79 tokens228 tokens
Pricing, USD per 1M tokens
Input$0.085Best$0.10
Output$0.46$0.30Best
Performance
Request success (24h)91.6%98.4%Best
Benchmark indexes
Intelligence Index6.56.6Best
Coding Index8.2—
Math Index14.021.7Best
Capabilities
ToolsYesNo
VisionYesNo
Structured outputYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • Llama 4 Scout
  • Qwen3 30B A3B

Intelligence Index

  • Llama 4 Scout6.5
  • Qwen3 30B A3B6.6

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
    • Qwen3 30B A3B: —

  • Math Index

    Composite of the math evaluations

    • Llama 4 Scout: 14.0
    • Qwen3 30B A3B: 21.7Top

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Llama 4 Scout: 0.2%
    • Qwen3 30B A3B: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Llama 4 Scout: 0.0%
    • Qwen3 30B A3B: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Llama 4 Scout: 0.0%
    • Qwen3 30B A3B: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Llama 4 Scout: 27.7%Top
    • Qwen3 30B A3B: 0.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Llama 4 Scout: 3.8%
    • Qwen3 30B A3B: 4.6%Top

  • GPQA Diamond

    Graduate-level science questions

    • Llama 4 Scout: 58.7%Top
    • Qwen3 30B A3B: 51.5%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Llama 4 Scout: 75.2%Top
    • Qwen3 30B A3B: 71.0%

  • IFBench

    Following precise output instructions

    • Llama 4 Scout: 39.5%Top
    • Qwen3 30B A3B: 31.9%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Llama 4 Scout: 0.0%
    • Qwen3 30B A3B: —

  • SciCode

    Scientific computing in Python

    • Llama 4 Scout: 21.3%
    • Qwen3 30B A3B: —

  • LiveCodeBench

    Recent competitive programming problems

    • Llama 4 Scout: 29.9%
    • Qwen3 30B A3B: 32.2%Top

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Llama 4 Scout: 14.0%
    • Qwen3 30B A3B: 21.7%Top

  • AIME

    Competition mathematics

    • Llama 4 Scout: 28.3%Top
    • Qwen3 30B A3B: 26.0%

  • MATH-500

    Competition math problems

    • Llama 4 Scout: 84.4%
    • Qwen3 30B A3B: 86.3%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Llama 4 Scout: 1.5%
    • Qwen3 30B A3B: 6.8%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Llama 4 Scout: 15.5%
    • Qwen3 30B A3B: 22.2%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Llama 4 Scout: 27.7%Top
    • Qwen3 30B A3B: 0.0%

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
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.