Compare AIFind AIAI NewsAI How-To
About Us
PrivacyTermsFAQContactContact
AIB Inc.Company info
© 2026 AIB Inc.
Meta
Meta

Llama 4 Maverick

Release Date 2025-04-05(Knowledge cutoff 2024-08-31)··1.0M IN · 16K OUTOpen Model(Llama)|API available
Overall1.5Top 95%Automation1.5Top 96%Office1.5Top 95%Coding1.5Top 95%

Llama 4 Maverick is Meta's high-capacity multimodal language model built on a Mixture-of-Experts architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input across 12 languages with a 1-million-token context window, and uses early fusion for native multimodality. Instruction-tuned for assistant-like interaction and image reasoning, Maverick is optimized for vision-language tasks requiring advanced multimodal understanding and high throughput.

  1. 01ImagesGenerated images
  2. 02CostCost · Usage · Speed
  3. 03User CompareUser Comparisons
  4. 04Expert EvalExpert Performance Evaluation
  5. 05OpinionPublic Opinion
  6. 06Related Info

API cost

Market price (median)
$0.27IN$0.85OUT
Price range3 providers
$0.188~$0.35IN$0.652~$1OUT
Calculate Cost
SourceOpenRouterLast updatedOct 7, 2026

Output Speed

Very slowper 2,000 tokens
First Output0.7s
total167s ›
12tok/s
First Output 0.7stotal: 167s ›
SourceOpenRouterLast updatedOct 8, 2026

User Comparisons

Response Speed
Total 20.4s
Total 20.4s
25 tok/s
SourceAIB Inc.Last updatedApr 10, 2026

Expert Performance Evaluation

Overall performance

MoreAll overall performance AI rankings
10.0132780.9%

About AA Intelligence IndexMore about AA Intelligence Index

Automation (agents)

MoreAll automation AI rankings
3.7%17.8%

About τ³-BankingMore about τ³-Banking

Documents and office work

MoreAll documents and office work AI rankings
50.0%131749.7%36.5%46.2%3.6%

About Long Context ReasoningMore about Long Context Reasoning

Research and fact-checking

MoreAll research and fact-checking AI rankings
QHow well can it predict what will happen?ForecastBench Brier Index·Bottom 15%#24
57.1

About ForecastBench Brier IndexMore about ForecastBench Brier Index

Coding

MoreAll coding AI rankings
0.0%13731737.9%6.8%16.339.7%31.7%24.5%15.6%1358

About Terminal-Bench 4.0More about Terminal-Bench 4.0

Writing and chat

MoreAll writing and chat AI rankings
1312132643.0%130713146.20 / 1054.2%1296

About Arena Writing, Literature & LanguageMore about Arena Writing, Literature & Language

Math and science

MoreAll math and science AI rankings
4.9%0.0%131667.1%20.6%19.319.3%1342131988.9%73.0%0.7%4.4%0.0%27.7%0.6%61.9%15.9

About Humanity's Last ExamMore about Humanity's Last Exam

Image understanding

MoreAll image understanding and analysis AI rankings
114252.0%31.8%

About Arena VisionMore about Arena Vision

Specialized fields

12611258133913261344134185.9%59.2%62.9%75.7%58.2%2.0%23.7%

About Arena KoreanMore about Arena Korean

See each evaluation’s detail page for its source and last update·Data sources & removal requests

Related Info

Meta
Public
Meta
🇺🇸 Menlo Park2023$1.9T~70,000 (total)
Muse Spark 1.3 ContributorMuse Spark 1.3Muse Spark 1.2Muse Spark 1.1Muse Image