Meta: Llama 4 Maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per for…

meta-llama/llama-4-maverick-17b-128e-instruct

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.

Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
524288
Knowledge cutoff
2024-08-31
Published model ID
Llama-4-Maverick-17B-128E-Instruct
Capabilities
multimodal, promptCaching, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

81–100 / 102

LMArena

1,289.296

source id
lmarena
leaderboard name
LMArena Text Multi Turn
dimension
general
metric
Arena rating
rank
258
sample size
6677
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1281.4649275502375
confidence upper
1297.1271945282851
Original result ↗

LMArena

1,295.296

source id
lmarena
leaderboard name
LMArena Text Hard Prompts English
dimension
general
metric
Arena rating
rank
259
sample size
7680
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1288.0120311895628
confidence upper
1302.5793431623536
Original result ↗

LMArena

1,266.503

source id
lmarena
leaderboard name
LMArena Text Creative Writing
dimension
general
metric
Arena rating
rank
259
sample size
5144
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1257.9469526011994
confidence upper
1275.059131403325
Original result ↗

LMArena

1,269.214

source id
lmarena
leaderboard name
LMArena Text Non English
dimension
general
metric
Arena rating
rank
260
sample size
20495
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1263.9578312739914
confidence upper
1274.4699498931855
Original result ↗

LMArena

1,301.404

source id
lmarena
leaderboard name
LMArena Text Coding
dimension
general
metric
Arena rating
rank
262
sample size
6934
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1293.9401125778288
confidence upper
1308.8670144211176
Original result ↗

LMArena

1,277.232

source id
lmarena
leaderboard name
LMArena Text Industry Writing And Literature And Language
dimension
general
metric
Arena rating
rank
262
sample size
8719
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1270.3346701198748
confidence upper
1284.1302684211014
Original result ↗

LMArena

1,275.545

source id
lmarena
leaderboard name
LMArena Text Industry Medicine And Healthcare
dimension
general
metric
Arena rating
rank
262
sample size
2290
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1262.3213071522096
confidence upper
1288.768429520666
Original result ↗

LMArena

1,339.803

source id
lmarena
leaderboard name
LMArena Text Style Control English
dimension
style
metric
Arena rating
rank
263
sample size
18892
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1334.41793097862
confidence upper
1345.1877091629576
Original result ↗

LMArena

1,266.982

source id
lmarena
leaderboard name
LMArena Text Instruction Following
dimension
general
metric
Arena rating
rank
263
sample size
10489
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1260.5213231964256
confidence upper
1273.4430405566798
Original result ↗

LMArena

1,280.569

source id
lmarena
leaderboard name
LMArena Text Hard Prompts
dimension
general
metric
Arena rating
rank
264
sample size
15851
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1274.857039236189
confidence upper
1286.2805189390892
Original result ↗

LMArena

1,220.519

source id
lmarena
leaderboard name
LMArena Text Exclude Ties
dimension
general
metric
Arena rating
rank
264
sample size
28078
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1214.5621902724777
confidence upper
1226.4753449705559
Original result ↗

LMArena

1,298.701

source id
lmarena
leaderboard name
LMArena Text Industry Software And It Services
dimension
general
metric
Arena rating
rank
265
sample size
12275
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1292.5629428064797
confidence upper
1304.8385567113912
Original result ↗

LMArena

1,287.261

source id
lmarena
leaderboard name
LMArena Text Overall
dimension
general
metric
Arena rating
rank
265
sample size
39397
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1283.0018548068426
confidence upper
1291.5205162251327
Original result ↗

LMArena

1,285.944

source id
lmarena
leaderboard name
LMArena Text Industry Legal And Government
dimension
general
metric
Arena rating
rank
266
sample size
2581
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1273.8080022664271
confidence upper
1298.0797968965712
Original result ↗

LMArena

1,260.62

source id
lmarena
leaderboard name
LMArena Text Industry Business And Management And Financial Operations
dimension
general
metric
Arena rating
rank
267
sample size
6120
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1252.5005571332476
confidence upper
1268.738921014298
Original result ↗

LMArena

1,249.816

source id
lmarena
leaderboard name
LMArena Text Industry Entertainment And Sports And Media
dimension
general
metric
Arena rating
rank
267
sample size
6915
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1242.2533096689142
confidence upper
1257.3796536970556
Original result ↗

LMArena

1,302.407

source id
lmarena
leaderboard name
LMArena Text English
dimension
general
metric
Arena rating
rank
270
sample size
18892
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1297.0603561485007
confidence upper
1307.7540740025156
Original result ↗

LMArena

1,287.605

source id
lmarena
leaderboard name
LMArena Text Industry Life And Physical And Social Science
dimension
general
metric
Arena rating
rank
271
sample size
6705
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1279.7274266359177
confidence upper
1295.4822168169903
Original result ↗

LMArena

1,279.568

source id
lmarena
leaderboard name
LMArena Text Longer Query
dimension
general
metric
Arena rating
rank
271
sample size
7065
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1272.1162830966255
confidence upper
1287.020185570979
Original result ↗

Published prices

1–3 / 3

Provider specifications & access

1–2 / 2

Llama-4-Maverick-17B-128E-Instruct ↗

source model id
publishers/hf-meta-llama/models/llama-4-maverick-17b-128e-instruct@001
hosting
vertex-self-deployed
platforms
  • Google Cloud Vertex AI
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Llama-4-Maverick-17B-128E-Instruct ↗

    source model id
    publishers/meta/models/llama4@llama-4-maverick-17b-128e-instruct
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      Safety assessments

      1–1 / 1

      Foundation Model Transparency Index 2025 ↗

      31 / 100

      source id
      stanfordFMTI
      canonical model id
      meta-llama/llama-4-maverick-17b-128e-instruct
      taxonomy
      transparency
      hazard category
      transparency
      hazard name
      Organization transparency
      policy area
      Meta
      assessment type
      organization-level disclosure
      metric
      disclosure_score
      result label
      31 / 100
      sample size
      100
      updated at
      2026-11-09T18:08:05.227Z

      Source specification observations

      1–3 / 3

      openRouter ↗

      field
      context_length
      value
      524288
      normalized value
      524288
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      knowledge_cutoff
      reported field
      knowledge_cutoff
      value
      2024-08-31
      normalized value
      2024-08-31
      precision
      day
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      max_output_tokens
      value
      32768
      normalized value
      32768
      scope
      source-model
      source id
      openRouter
      confidence
      1

      Original sources

      1–14 / 14

      ai.meta.com · Model reference ↗

      Hugging Face · meta-llama/Llama-4-Maverick-17B-128E-Instruct ↗

      Google Cloud · Model page ↗

      Google Cloud · Model page ↗

      OpenRouter · Model page ↗

      Epoch AI · Catalog ↗

      GitHub · Catalog ↗

      GitHub · Catalog ↗

      Google Cloud · Catalog ↗

      Hugging Face · Catalog ↗

      LMArena · Catalog ↗

      OpenRouter · Catalog ↗

      OpenRouter · Catalog ↗

      livebench.ai · Catalog ↗

      Source links

      1–11 / 11

      Explore more models

      Models

      Loading
      EVIDENCE / COMPARISON

      Benchmarks

      Explore every benchmark

      Loading

      These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

      Install TensorTrace