Meta
Llama 4 Maverick
Quality Score17.6
Value Score16.9
Reliability29.1
Cache Discount6%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.260
- Output
- $0.910
- Cached Input
- $0.245
- Cached Output
- not available
- Cost per task
- $0.035
Capability
- Intelligence
- 14.5
- Coding
- 16.3
- Agentic
- 1.2
- Omniscience
- -41.9
- Correct
- 24.9%
- Blended price
- $0.314
Answer outcomes
Correct 24.9%Incorrect 66.8%Abstained 8.4%
Artificial Analysis benchmarks
- GDPval-AA v2
- 0%
- τ³-Banking
- 4%
- Terminal-Bench v2.1
- 8%
- SciCode
- 33%
- Humanity’s Last Exam
- 5%
- GPQA Diamond
- 67%
- CritPt
- 0%
- AA-Omniscience
- 29%
- AA-LCR
- 50%
Similar models
- Llama 3.1 Instruct 405BMetaQuality Score 21.4Value Score not available
- Llama 3.3 Instruct 70BMetaQuality Score 12.6Value Score 10.4
- Llama 4 ScoutMetaQuality Score 10.7Value Score 11.7
- Llama 3.2 Instruct 11B (Vision)MetaQuality Score 5.6Value Score 4.7
- Muse Glimmer (high)MetaQuality Score 34.2Value Score 34.0
- Muse Spark 1.2 (xhigh)MetaQuality Score 68.6Value Score 50.0