Llama 4 Scout
Not tested yet
Language modelActive
Llama 4 Scout
Meta
- Released
- April 2025
- Data date
- September 8, 2026
- Intelligence
- Overall score
- Speed
- 92.7 tokens/sOutput throughput
- Price
- Input · Output / 1M tokens
- Input
- Text, Image
- Output
- Text
No published category-wide ranking is available for this model.
Entries 1-12 of 22. Page 1 of 2.
Published benchmarks
Each chart compares models in the same documented test and highlights the current model.
VisualToolBench
Overall
What this benchmark measures: 1,204 visual tasks require image manipulation, Python, web search, or calculator use with at most 20 tool calls.
Context: The score belongs to the complete multimodal tool system and cannot isolate the model alone.
Higher is better10 modelsLlama 4 Scout: Rank 9 of 10Data date: August 26, 2026
Scale: 0% - 100%
Methodology and context
- Comparison cohort
- scale-visual-toolbench-apr
- Metric
- average pass rate
- Scale
- 0-100
- Participants
- 10
- Methodology and context
- 1,204 tasks, six tools, and at most 20 tool calls per task.. Source model ID: curated/llama-4-scout. Source model name: Llama 4 Scout. Provider reported by source: Meta. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 1.58% ± 0.04. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-7822fbb7c5cc. Source payload hash: 7822fbb7c5ccfaf05dab72443f6fe33aacc3c4831ec7684f25300ddcc9159ea1. Parser version: curated-v1. Imported at: 2026-09-04
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
MMMU (Show measurement, test conditions, and source)
- Source value
- 69.4
- Score
- 69.4
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:0
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned table; BF16
MMMU Pro (Show measurement, test conditions, and source)
- Source value
- 52.2
- Score
- 52.2
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:1
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned table; BF16
MathVista (Show measurement, test conditions, and source)
- Source value
- 70.7
- Score
- 70.7
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:2
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned table; BF16
ChartQA (Show measurement, test conditions, and source)
- Source value
- 88.8
- Score
- 88.8
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:3
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned table; BF16
DocVQA (Show measurement, test conditions, and source)
- Source value
- 94.4
- Score
- 94.4
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:4
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned table; BF16
LiveCodeBench (Show measurement, test conditions, and source)
- Source value
- 32.8
- Score
- 32.8
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:5
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned table; BF16
MMLU Pro instruct (Show measurement, test conditions, and source)
- Source value
- 74.3
- Score
- 74.3
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:6
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned table; BF16
GPQA (Show measurement, test conditions, and source)
- Source value
- 57.2
- Score
- 57.2
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:7
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned table; BF16
MGSM (Show measurement, test conditions, and source)
- Source value
- 90.6
- Score
- 90.6
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:8
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned table; BF16
MTOB half (Show measurement, test conditions, and source)
- Source value
- 54
- Score
- 54
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:9
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned tool-use table; BF16
MTOB full (Show measurement, test conditions, and source)
- Source value
- 50.8
- Score
- 50.8
- Metric
- percent
- Unit
- %
- Direction
- Higher is better
- Comparison cohort
- research:llama-4-scout:10
- Source type
- vendor-reported
- Evaluator
- Meta Llama 4 model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. Instruction-tuned tool-use table; BF16
Recorded measurement details
Every observation retains its source value and published test conditions.
VisualToolBench: Overall (Show measurement, test conditions, and source)
- Source value
- 1.58
- Score
- 1.58
- Metric
- average pass rate
- Unit
- %
- Benchmark version
- 1,204-task release
- Category
- multimodal
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- scale-visual-toolbench-apr
- Confidence interval
- 0.04
- Source type
- official-leaderboard
- Evaluator
- Scale AI
- Status
- active
- Retrieved at
- 2026-08-26
- Methodology
- 1,204 tasks, six tools, and at most 20 tool calls per task.. Source model ID: curated/llama-4-scout. Source model name: Llama 4 Scout. Provider reported by source: Meta. Evaluator: Scale AI. Dataset type: public. Attempts: pass@1. Score display: 1.58% ± 0.04. Source ID: scale-ai. Evidence capture ID: curated-scale-ai-2026-08-26-7822fbb7c5cc. Source payload hash: 7822fbb7c5ccfaf05dab72443f6fe33aacc3c4831ec7684f25300ddcc9159ea1. Parser version: curated-v1. Imported at: 2026-09-04
- Comparison methodology
- 1,204 tasks, six tools, and at most 20 tool calls per task.
Our model tests
Community tests you can inspect
Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.
Pelican on a bicycle
A community classic for free-form SVG drawing.
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)Profile
Specifications and access
Published information about this model. Existing estimates are explicitly labeled.
Additional source observations
Dated documentation and model-card observations. Provider limits, native context and extended context can differ. Configuration notes retain the source wording.
- License
- Llama 4 Community LicenseSource
- Release
- 2025-04-05Source
- Parameters
- 109 BSource
- Active parameters
- 17 BSource
- Architecture
- early-fusion sparse mixture-of-expertsSource
- Context window
- 10,485,760 tokensSource
- Input
- Text, ImageSource
- Output
- Text, codeSource
- Languages
- 12Source
- Training tokens
- ~40TSource
- Knowledge cutoff
- 2024-08Source
Pricing
Published prices
Prices apply to the stated unit. Resolution, output length, and provider can change the cost.
Cost example
100 API requests
$0.025
100 requests with 1,000 input and 500 output tokens each calculate to $0.025. Input accounts for $0.01; output accounts for $0.015.
- Input price
- $0.1 / 1M tokensBase tier for each request
- Output price
- $0.3 / 1M tokensBase tier for each request
The calculation uses documented token prices and no cache discount. It excludes extra tools, tax, reasoning tokens, and further hidden output tokens.
Open sourceHead-to-head comparisons
Compare this model
Each matchup compares this model with exactly one other model from the same category.
There are no published direct comparisons for this model yet.
Evidence
Sources and data date
Every statement links to its underlying documentation or leaderboard.
- Speed
Median across serving providers. Output speed after the first streaming chunk, not total response time. Retrieved September 8, 2026.
- Price
Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs.
- Input
Documented modalities. Retrieved September 8, 2026.
- Output
Documented modalities. Retrieved September 8, 2026.
Research date September 8, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Open evidence questions and research notes (original wording)
Not found in the inspected sources
max-output-tokens. Card does not specify a model-specific maximum output.