Llama 4 Scout

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

Meta: Llama 4 Scout, released on 2025-04-05 by meta-llama, accepts text and image inputs and generates text output with a context length of 10,000,000 tokens. The model costs $0

  • tool use
  • structured outputs

At a glance

providermeta-llama
releasedJan 1, 2025
context1.3M
input / M$0.100

Specifications

What the API gives you

Context window
1.3M tokens
Max output
16K tokens
Input price
$0.100 / 1M tokens
Output price
$0.30 / 1M tokens
Cache read
Modalities
text, image → text
Knowledge cutoff
Aug 31, 2024
Released
Jan 1, 2025

Measured evidence

Public benchmark record

BFCL
28.1%2026-07-28
BFCL
28.1%2026-07-27
BFCL
28.1%2026-07-29
BFCL
28.1%2026-07-30
BFCL
28.1%2026-07-31
BFCL
28.1%2026-08-02
BFCL
28.1%2026-08-01
BFCL
28.1%2026-08-05
BFCL
28.1%2026-08-03
BFCL
28.1%2026-08-09
BFCL
28.1%2026-08-04
BFCL
28.1%2026-08-06
BFCL
28.1%2026-08-07
BFCL
28.1%2026-08-10
BFCL
28.1%2026-08-14
BFCL
28.1%2026-08-08
BFCL
28.1%2026-08-11
BFCL
28.1%2026-08-18
BFCL
28.1%2026-08-15
BFCL
28.1%2026-08-12
BFCL
28.1%2026-08-13
BFCL
28.1%2026-08-19
BFCL
28.1%2026-08-16
BFCL
28.1%2026-08-20
BFCL
28.1%2026-08-27
BFCL
28.1%2026-08-17
BFCL
28.1%2026-08-21
BFCL
28.1%2026-08-22
BFCL
28.1%2026-08-23
BFCL
28.1%2026-08-24
BFCL
28.1%2026-08-28
BFCL
28.1%2026-09-05
BFCL
28.1%2026-08-25
BFCL
28.1%2026-08-26
BFCL
28.1%2026-09-06
BFCL
28.1%2026-08-29
BFCL
28.1%2026-08-30
BFCL
28.1%2026-08-31
BFCL
28.1%2026-09-01
BFCL
28.1%2026-09-02
BFCL
28.1%2026-09-03
BFCL
28.1%2026-09-04
Design Arena Coding
820 Elo2026-07-28
Design Arena Coding
820 Elo2026-07-27
Design Arena Coding
820 Elo2026-07-30
Design Arena Coding
820 Elo2026-07-29
Design Arena Coding
820 Elo2026-07-31
Design Arena Coding
819 Elo2026-08-02
Design Arena Coding
818 Elo2026-08-05
Design Arena Coding
819 Elo2026-08-01
Design Arena Coding
817 Elo2026-08-09
Design Arena Coding
819 Elo2026-08-03
Design Arena Coding
819 Elo2026-08-04
Design Arena Coding
815 Elo2026-08-14
Design Arena Coding
819 Elo2026-08-06
Design Arena Coding
817 Elo2026-08-10
Design Arena Coding
819 Elo2026-08-07
Design Arena Coding
809 Elo2026-08-18
Design Arena Coding
818 Elo2026-08-08
Design Arena Coding
809 Elo2026-08-15
Design Arena Coding
817 Elo2026-08-11
Design Arena Coding
816 Elo2026-08-12
Design Arena Coding
815 Elo2026-08-13
Design Arena Coding
807 Elo2026-08-19
Design Arena Coding
814 Elo2026-08-27
Design Arena Coding
807 Elo2026-08-20
Design Arena Coding
809 Elo2026-08-16
Design Arena Coding
806 Elo2026-09-05
Design Arena Coding
808 Elo2026-08-17
Design Arena Coding
814 Elo2026-08-21
Design Arena Coding
814 Elo2026-08-22
Design Arena Coding
814 Elo2026-08-23
Design Arena Coding
814 Elo2026-08-28
Design Arena Coding
814 Elo2026-08-24
Design Arena Coding
815 Elo2026-08-25
Design Arena Coding
815 Elo2026-08-26
Design Arena Coding
806 Elo2026-09-06
Design Arena Coding
814 Elo2026-08-29
Design Arena Coding
813 Elo2026-08-30
Design Arena Coding
813 Elo2026-08-31
Design Arena Coding
813 Elo2026-09-01
Design Arena Coding
812 Elo2026-09-02
Design Arena Coding
810 Elo2026-09-03
Design Arena Coding
809 Elo2026-09-04
Design Arena UI
804 Elo2026-07-28
Design Arena UI
805 Elo2026-07-27
Design Arena UI
805 Elo2026-07-30
Design Arena UI
805 Elo2026-07-29
Design Arena UI
804 Elo2026-07-31
Design Arena UI
805 Elo2026-08-02
Design Arena UI
805 Elo2026-08-01
Design Arena UI
804 Elo2026-08-05
Design Arena UI
805 Elo2026-08-03
Design Arena UI
801 Elo2026-08-09
Design Arena UI
804 Elo2026-08-04
Design Arena UI
799 Elo2026-08-14
Design Arena UI
803 Elo2026-08-06
Design Arena UI
803 Elo2026-08-07
Design Arena UI
801 Elo2026-08-10
Design Arena UI
801 Elo2026-08-08
Design Arena UI
795 Elo2026-08-18
Design Arena UI
801 Elo2026-08-11
Design Arena UI
796 Elo2026-08-15
Design Arena UI
801 Elo2026-08-12
Design Arena UI
802 Elo2026-08-13
Design Arena UI
795 Elo2026-08-19
Design Arena UI
796 Elo2026-08-16
Design Arena UI
795 Elo2026-08-20
Design Arena UI
794 Elo2026-08-27
Design Arena UI
795 Elo2026-08-17
Design Arena UI
790 Elo2026-09-05
Design Arena UI
794 Elo2026-08-21
Design Arena UI
794 Elo2026-08-22
Design Arena UI
795 Elo2026-08-23
Design Arena UI
795 Elo2026-08-24
Design Arena UI
794 Elo2026-08-28
Design Arena UI
795 Elo2026-08-25
Design Arena UI
795 Elo2026-08-26
Design Arena UI
790 Elo2026-09-06
Design Arena UI
794 Elo2026-08-29
Design Arena UI
794 Elo2026-08-30
Design Arena UI
794 Elo2026-08-31
Design Arena UI
794 Elo2026-09-01
Design Arena UI
793 Elo2026-09-02
Design Arena UI
791 Elo2026-09-03
Design Arena UI
790 Elo2026-09-04
Design Arena Website
775 Elo2026-07-28
Design Arena Website
775 Elo2026-07-30
Design Arena Website
775 Elo2026-07-27
Design Arena Website
775 Elo2026-07-29
Design Arena Website
774 Elo2026-07-31
Design Arena Website
774 Elo2026-08-02
Design Arena Website
774 Elo2026-08-01
Design Arena Website
773 Elo2026-08-05
Design Arena Website
774 Elo2026-08-03
Design Arena Website
772 Elo2026-08-09
Design Arena Website
774 Elo2026-08-04
Design Arena Website
770 Elo2026-08-14
Design Arena Website
773 Elo2026-08-06
Design Arena Website
774 Elo2026-08-07
Design Arena Website
772 Elo2026-08-10
Design Arena Website
772 Elo2026-08-08
Design Arena Website
761 Elo2026-08-18
Design Arena Website
772 Elo2026-08-11
Design Arena Website
761 Elo2026-08-15
Design Arena Website
772 Elo2026-08-12
Design Arena Website
770 Elo2026-08-13
Design Arena Website
761 Elo2026-08-19
Design Arena Website
761 Elo2026-08-16
Design Arena Website
761 Elo2026-08-20
Design Arena Website
770 Elo2026-08-27
Design Arena Website
761 Elo2026-08-17
Design Arena Website
766 Elo2026-09-05
Design Arena Website
770 Elo2026-08-21
Design Arena Website
770 Elo2026-08-22
Design Arena Website
770 Elo2026-08-23
Design Arena Website
770 Elo2026-08-24
Design Arena Website
770 Elo2026-08-28
Design Arena Website
770 Elo2026-08-25
Design Arena Website
770 Elo2026-08-26
Design Arena Website
763 Elo2026-09-06
Design Arena Website
770 Elo2026-08-29
Design Arena Website
769 Elo2026-08-30
Design Arena Website
769 Elo2026-08-31
Design Arena Website
769 Elo2026-09-01
Design Arena Website
768 Elo2026-09-02
Design Arena Website
766 Elo2026-09-03
Design Arena Website
765 Elo2026-09-04
LMArena Creative Writing
1251 Elo2026-07-21
LMArena Creative Writing
1250 Elo2026-07-27
LMArena Creative Writing
1250 Elo2026-07-30
LMArena Creative Writing
1250 Elo2026-08-02
LMArena Creative Writing
1250 Elo2026-08-03
LMArena Creative Writing
1250 Elo2026-08-06
LMArena Creative Writing
1250 Elo2026-08-12
LMArena Creative Writing
1250 Elo2026-08-21
LMArena Creative Writing
1249 Elo2026-09-02
LMArena Creative Writing
1249 Elo2026-08-27
LMArena Creative Writing
1249 Elo2026-09-01
LMArena Long Query
1268 Elo2026-07-21
LMArena Long Query
1268 Elo2026-07-27
LMArena Long Query
1268 Elo2026-07-30
LMArena Long Query
1268 Elo2026-08-02
LMArena Long Query
1268 Elo2026-08-03
LMArena Long Query
1268 Elo2026-08-06
LMArena Long Query
1266 Elo2026-08-12
LMArena Long Query
1266 Elo2026-08-21
LMArena Long Query
1265 Elo2026-09-02
LMArena Long Query
1265 Elo2026-08-27
LMArena Long Query
1266 Elo2026-09-01
LMArena Math
1286 Elo2026-07-21
LMArena Math
1286 Elo2026-07-27
LMArena Math
1286 Elo2026-07-30
LMArena Math
1286 Elo2026-08-02
LMArena Math
1286 Elo2026-08-03
LMArena Math
1286 Elo2026-08-06
LMArena Math
1286 Elo2026-08-12
LMArena Math
1286 Elo2026-08-21
LMArena Math
1286 Elo2026-09-01
LMArena Math
1286 Elo2026-08-27
LMArena Text
1323 Elo2026-07-21
LMArena Text
1323 Elo2026-07-27
LMArena Text
1323 Elo2026-07-30
LMArena Text
1323 Elo2026-08-02
LMArena Text
1322 Elo2026-08-10
LMArena Text
1323 Elo2026-08-06
LMArena Text
1323 Elo2026-08-03
LMArena Text
1322 Elo2026-08-21
LMArena Text
1322 Elo2026-08-12
LMArena Text
1321 Elo2026-09-01
LMArena Text
1321 Elo2026-09-02
LMArena Text
1321 Elo2026-08-27
LMArena Vision
1118 Elo2026-07-12
LMArena Vision
1128 Elo2026-07-21
LMArena Vision
1128 Elo2026-07-26
LMArena Vision
1128 Elo2026-07-30
LMArena Vision
1128 Elo2026-08-02
LMArena Vision
1128 Elo2026-08-06
LMArena Vision
1128 Elo2026-08-21
LMArena Vision
1128 Elo2026-08-27
SWE-rebench
6.6% ± 0.22025-08-01text

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Business WritingProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • 70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • 65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Search. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for WritingProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Frontend & UIProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenClawProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • 55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Reasoning or VLMEvalKit tasks. 3 of 4 configured evaluation feeds currently have results.

  • 55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • 50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsProvisional evidence

    50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.

  • 40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for CodingProvisional evidence

    40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 8 of 8 configured evaluation feeds currently have results.

  • Best LLM for Competition MathProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best Value LLMProvisional evidence

    36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Autonomous AgentsProvisional evidence

    29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesProvisional evidence

    29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Cheapest Capable LLMProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Charts & DiagramsProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingProvisional evidence

    23% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps. 8 of 8 configured evaluation feeds currently have results.

  • 20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • 20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 4 of 4 configured evaluation feeds currently have results.

  • Best Local LLM for CodingProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 5 of 5 configured evaluation feeds currently have results.

  • 18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.

  • 13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionProvisional evidence

    13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.