Swiss AI Initiative
Apertus 8B Instruct
Quality Score3.4
Value Score3.2
Reliability11.4
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 65,536 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.100
- Output
- $0.200
- Cached Input
- not available
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 1.0
- Coding
- not available
- Agentic
- not available
- Omniscience
- -77.2
- Correct
- 9.7%
- Blended price
- $0.110
Answer outcomes
Correct 9.7%Incorrect 86.9%Abstained 3.5%
Artificial Analysis benchmarks
- SciCode
- 4%
- Humanity’s Last Exam
- 5%
- GPQA Diamond
- 26%
- CritPt
- 0%
- AA-Omniscience
- 11%
- AA-LCR
- 0%
Similar models
- Apertus 70B InstructSwiss AI InitiativeQuality Score 5.7Value Score 3.7
- LFM2 8B A1BLiquid AIQuality Score 3.2Value Score not available
- LFM2.5-1.2B-InstructLiquid AIQuality Score 3.5Value Score not available
- Olmo 3 7B InstructAllen Institute for AIQuality Score 3.4Value Score 3.8
- Granite 4.0 MicroIBMQuality Score 3.7Value Score not available
- LFM2 2.6BLiquid AIQuality Score 3.8Value Score not available