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

41–60 / 102

LMArena

1,150.65

source id
lmarena
leaderboard name
LMArena Vision Style Control English
dimension
multimodal
metric
Arena rating
rank
124
sample size
3378
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1138.8236476416355
confidence upper
1162.4757799918439
Original result ↗

LMArena

1,330.572

source id
lmarena
leaderboard name
LMArena Text Style Control German
dimension
style
metric
Arena rating
rank
195
sample size
1028
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1311.5272783062564
confidence upper
1349.616688369045
Original result ↗

LMArena

1,257.516

source id
lmarena
leaderboard name
LMArena Text Style Control Japanese
dimension
style
metric
Arena rating
rank
199
sample size
935
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1236.2753506178324
confidence upper
1278.7558373801721
Original result ↗

LMArena

1,330.323

source id
lmarena
leaderboard name
LMArena Text Style Control Polish
dimension
style
metric
Arena rating
rank
201
sample size
2675
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1317.6134519499822
confidence upper
1343.0321168091816
Original result ↗

LMArena

1,290.296

source id
lmarena
leaderboard name
LMArena Text German
dimension
general
metric
Arena rating
rank
207
sample size
1028
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1271.2784401141507
confidence upper
1309.3131483647687
Original result ↗

LMArena

1,206.556

source id
lmarena
leaderboard name
LMArena Text Japanese
dimension
general
metric
Arena rating
rank
215
sample size
935
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1185.2973415203558
confidence upper
1227.8138445041177
Original result ↗

LMArena

1,262.296

source id
lmarena
leaderboard name
LMArena Text Style Control Korean
dimension
style
metric
Arena rating
rank
216
sample size
796
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1240.3605544493685
confidence upper
1284.231256437853
Original result ↗

LMArena

1,275.433

source id
lmarena
leaderboard name
LMArena Text Polish
dimension
general
metric
Arena rating
rank
217
sample size
2675
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1262.866071200879
confidence upper
1287.9997050117227
Original result ↗

LMArena

1,292.807

source id
lmarena
leaderboard name
LMArena Text Spanish
dimension
general
metric
Arena rating
rank
219
sample size
816
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1271.3151411965798
confidence upper
1314.2981282712099
Original result ↗

LMArena

1,203.467

source id
lmarena
leaderboard name
LMArena Text Korean
dimension
general
metric
Arena rating
rank
221
sample size
796
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1181.5186201344102
confidence upper
1225.4146490165779
Original result ↗

LMArena

1,325.396

source id
lmarena
leaderboard name
LMArena Text Style Control Spanish
dimension
style
metric
Arena rating
rank
222
sample size
816
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1303.9113805067054
confidence upper
1346.8799094158708
Original result ↗

LMArena

1,307.251

source id
lmarena
leaderboard name
LMArena Text Style Control Creative Writing
dimension
style
metric
Arena rating
rank
230
sample size
5144
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1298.6591785344185
confidence upper
1315.8423500891693
Original result ↗

LMArena

1,328.019

source id
lmarena
leaderboard name
LMArena Text Style Control Russian
dimension
style
metric
Arena rating
rank
234
sample size
3099
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1317.5647358715978
confidence upper
1338.4729145128022
Original result ↗

LMArena

1,316.945

source id
lmarena
leaderboard name
LMArena Text Style Control Math
dimension
style
metric
Arena rating
rank
236
sample size
2820
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1306.053607521288
confidence upper
1327.8367636053654
Original result ↗

LMArena

1,344.463

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Medicine And Healthcare
dimension
style
metric
Arena rating
rank
242
sample size
2290
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1331.1926329541343
confidence upper
1357.7340205480753
Original result ↗

LMArena

1,341.206

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Legal And Government
dimension
style
metric
Arena rating
rank
242
sample size
2581
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1329.058901286686
confidence upper
1353.3524329405009
Original result ↗

LMArena

1,325.523

source id
lmarena
leaderboard name
LMArena Text Style Control Expert
dimension
style
metric
Arena rating
rank
242
sample size
2013
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1312.1556728753783
confidence upper
1338.8896837710472
Original result ↗

LMArena

1,259.349

source id
lmarena
leaderboard name
LMArena Text French
dimension
general
metric
Arena rating
rank
243
sample size
596
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1233.8908528107258
confidence upper
1284.8070092238072
Original result ↗

LMArena

1,326.442

source id
lmarena
leaderboard name
LMArena Text Style Control Multi Turn
dimension
style
metric
Arena rating
rank
244
sample size
6677
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1318.5887678155182
confidence upper
1334.2946152386903
Original result ↗

LMArena

1,312.034

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Writing And Literature And Language
dimension
style
metric
Arena rating
rank
244
sample size
8719
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Maverick 17B 128E Instruct
confidence lower
1305.0941683253905
confidence upper
1318.9734928952744
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