Meta
Llama 3.3 Instruct 70B
Quality Score12.6
Value Score10.4
Reliability22.9
Cache Discount0%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 128k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.655
- Output
- $0.720
- Cached Input
- $0.655
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 9.3
- Coding
- 11.9
- Agentic
- not available
- Omniscience
- -54.2
- Correct
- 18.9%
- Blended price
- $0.662
Answer outcomes
Correct 18.9%Incorrect 73.1%Abstained 7.9%
Artificial Analysis benchmarks
- GDPval-AA v2
- 0%
- Terminal-Bench v2.1
- 5%
- SciCode
- 26%
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 50%
- CritPt
- 0%
- AA-Omniscience
- 23%
- AA-LCR
- 16%
Similar models
- Llama 4 ScoutMetaQuality Score 10.7Value Score 11.7
- Llama 4 MaverickMetaQuality Score 17.6Value Score 16.9
- Llama 3.1 Instruct 405BMetaQuality Score 21.4Value Score not available
- Llama 3.2 Instruct 11B (Vision)MetaQuality Score 5.6Value Score 4.7
- Muse Glimmer (high)MetaQuality Score 34.2Value Score 34.0
- Llama 3.2 Instruct 90B (Vision)MetaQuality Score not availableValue Score not available