Meta
Llama 4 Scout
Quality Score10.7
Value Score11.7
Reliability23.9
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 10M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.180
- Output
- $0.660
- Cached Input
- not available
- Cached Output
- not available
- Cost per task
- $0.011
Capability
- Intelligence
- 10.3
- Coding
- 8.2
- Agentic
- 1.1
- Omniscience
- -52.1
- Correct
- 15.2%
- Blended price
- $0.228
Answer outcomes
Correct 15.2%Incorrect 67.3%Abstained 17.5%
Artificial Analysis benchmarks
- GDPval-AA v2
- 0%
- τ³-Banking
- 3%
- Terminal-Bench v2.1
- 4%
- SciCode
- 17%
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 59%
- CritPt
- 0%
- AA-Omniscience
- 24%
- AA-LCR
- 30%
Similar models
- Llama 3.3 Instruct 70BMetaQuality Score 12.6Value Score 10.4
- Llama 3.2 Instruct 11B (Vision)MetaQuality Score 5.6Value Score 4.7
- Llama 4 MaverickMetaQuality Score 17.6Value Score 16.9
- Llama 3.1 Instruct 405BMetaQuality Score 21.4Value Score not available
- Muse Glimmer (high)MetaQuality Score 34.2Value Score 34.0
- Llama 3.2 Instruct 90B (Vision)MetaQuality Score not availableValue Score not available