Meta: Llama 4 Scout

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and…

meta-llama/llama-4-scout-17b-16e-instruct

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.

Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
1310720
Knowledge cutoff
2024-08-31
Published model ID
Llama-4-Scout-17B-16E-Instruct
Capabilities
multimodal, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

21–40 / 95

LMArena

1,138.96

source id
lmarena
leaderboard name
LMArena Vision Style Control Creative Writing Vision
dimension
multimodal
metric
Arena rating
rank
102
sample size
238
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1097.634028616059
confidence upper
1180.2861085263082
Original result ↗

LMArena

1,126.78

source id
lmarena
leaderboard name
LMArena Vision Creative Writing Vision
dimension
multimodal
metric
Arena rating
rank
103
sample size
238
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1085.7187897913136
confidence upper
1167.841501698886
Original result ↗

LMArena

1,127.35

source id
lmarena
leaderboard name
LMArena Vision Style Control Chinese
dimension
multimodal
metric
Arena rating
rank
112
sample size
278
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1091.3272200984443
confidence upper
1163.3723953632834
Original result ↗

LMArena

1,105.997

source id
lmarena
leaderboard name
LMArena Vision Chinese
dimension
multimodal
metric
Arena rating
rank
113
sample size
278
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1069.683822106247
confidence upper
1142.3109593024142
Original result ↗

LMArena

1,149.243

source id
lmarena
leaderboard name
LMArena Vision Homework
dimension
multimodal
metric
Arena rating
rank
116
sample size
474
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1123.141793938162
confidence upper
1175.3445195129375
Original result ↗

LMArena

1,148.948

source id
lmarena
leaderboard name
LMArena Vision Style Control Homework
dimension
multimodal
metric
Arena rating
rank
116
sample size
474
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1122.6233830183212
confidence upper
1175.271797744451
Original result ↗

LMArena

1,150.944

source id
lmarena
leaderboard name
LMArena Vision Style Control Diagram
dimension
multimodal
metric
Arena rating
rank
117
sample size
843
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1130.812321459064
confidence upper
1171.0764063664797
Original result ↗

LMArena

1,125.028

source id
lmarena
leaderboard name
LMArena Vision Diagram
dimension
multimodal
metric
Arena rating
rank
120
sample size
843
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1104.8312667374225
confidence upper
1145.2248506377305
Original result ↗

LMArena

1,116.474

source id
lmarena
leaderboard name
LMArena Vision Ocr
dimension
multimodal
metric
Arena rating
rank
121
sample size
2779
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1103.9986802113037
confidence upper
1128.9492293985809
Original result ↗

LMArena

1,131.109

source id
lmarena
leaderboard name
LMArena Vision Style Control Ocr
dimension
multimodal
metric
Arena rating
rank
122
sample size
2779
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1118.5705273125845
confidence upper
1143.6467026868665
Original result ↗

LMArena

1,144.909

source id
lmarena
leaderboard name
LMArena Vision Style Control English
dimension
multimodal
metric
Arena rating
rank
126
sample size
3094
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1132.3576135076323
confidence upper
1157.4612314896976
Original result ↗

LMArena

1,143.013

source id
lmarena
leaderboard name
LMArena Vision English
dimension
multimodal
metric
Arena rating
rank
126
sample size
3094
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1130.575538477624
confidence upper
1155.4496471041073
Original result ↗

LMArena

1,127.635

source id
lmarena
leaderboard name
LMArena Vision Style Control Overall
dimension
multimodal
metric
Arena rating
rank
127
sample size
6431
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1118.1192047484983
confidence upper
1137.1517215183835
Original result ↗

LMArena

1,118.38

source id
lmarena
leaderboard name
LMArena Vision Overall
dimension
multimodal
metric
Arena rating
rank
129
sample size
6431
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1108.9299142863047
confidence upper
1127.829343417442
Original result ↗

LMArena

1,258.843

source id
lmarena
leaderboard name
LMArena Text Style Control Japanese
dimension
style
metric
Arena rating
rank
198
sample size
764
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1236.3736688118388
confidence upper
1281.31215435385
Original result ↗

LMArena

1,322.169

source id
lmarena
leaderboard name
LMArena Text Style Control Polish
dimension
style
metric
Arena rating
rank
205
sample size
2466
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1308.9786605928507
confidence upper
1335.3587281249952
Original result ↗

LMArena

1,269.165

source id
lmarena
leaderboard name
LMArena Text Style Control Korean
dimension
style
metric
Arena rating
rank
208
sample size
649
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1243.8293652704328
confidence upper
1294.5002139639535
Original result ↗

LMArena

1,311.085

source id
lmarena
leaderboard name
LMArena Text Style Control German
dimension
style
metric
Arena rating
rank
214
sample size
799
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1289.4707293709255
confidence upper
1332.6998632099294
Original result ↗

LMArena

1,206.694

source id
lmarena
leaderboard name
LMArena Text Japanese
dimension
general
metric
Arena rating
rank
214
sample size
764
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1184.3611497508127
confidence upper
1229.0273017841541
Original result ↗

LMArena

1,207.17

source id
lmarena
leaderboard name
LMArena Text Korean
dimension
general
metric
Arena rating
rank
218
sample size
649
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 4 Scout 17B 16E Instruct
confidence lower
1181.9623996740343
confidence upper
1232.3783951252524
Original result ↗

Published prices

1–6 / 6

Provider specifications & access

1–3 / 3

llama-4-scout-17b-16e-instruct ↗

source model id
@cf/meta/llama-4-scout-17b-16e-instruct
hosting
cloudflare-hosted
platforms
  • Cloudflare Workers AI
context length
131000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • toolCalling

Llama-4-Scout-17B-16E-Instruct ↗

source model id
publishers/hf-meta-llama/models/llama-4-scout-17b-16e-instruct@001
hosting
vertex-self-deployed
platforms
  • Google Cloud Vertex AI
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Llama-4-Scout-17B-16E-Instruct ↗

    source model id
    publishers/meta/models/llama4@llama-4-scout-17b-16e-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-scout-17b-16e-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
      1310720
      normalized value
      1310720
      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
      16384
      normalized value
      16384
      scope
      source-model
      source id
      openRouter
      confidence
      1

      Original sources

      1–17 / 17

      ai.meta.com · Model reference ↗

      Hugging Face · Model reference ↗

      Cloudflare AI · Model page ↗

      DeepInfra · Model page ↗

      Google Cloud · Model page ↗

      Google Cloud · Model page ↗

      OpenRouter · Model page ↗

      GitHub · Source snapshot ↗

      Cloudflare AI · Catalog ↗

      DeepInfra · Catalog ↗

      Epoch AI · Catalog ↗

      GitHub · Catalog ↗

      GitHub · Catalog ↗

      Google Cloud · Catalog ↗

      LMArena · Catalog ↗

      OpenRouter · Catalog ↗

      gorilla.cs.berkeley.edu · Catalog ↗

      Source links

      1–12 / 12

      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