readable AI benchmarks (simplified)
Swiss AI Initiative
Apertus 70B Instruct
Apertus 70B Instruct has a Quality Score of 13.5, ranking 519th among 571 scored models. Per 1M tokens, pricing is $0.820 input and $2.92 output. It has a 65,536 token context window. Its Reliability Score is 19.2, ranking 487th among 573 scored models, below average (total average: 36.5).
Quality Score13.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability19.2
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 65,536 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.820
- Output
- $2.92
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 5.1
- Coding
- not available
- Agentic
- not available
- Omniscience
- -61.5
- Correct
- 11.6%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 84.8%
Correct 11.6%Incorrect 73.2%Partial / not attempted 15.2%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 5%
- GPQA Diamond
- 27%
- CritPt
- 0%
- AA-Omniscience
- 19%
- AA-LCR
- 0%
Similar models
- Apertus 8B InstructSwiss AI InitiativeQuality Score 9.4Value Score not available
- Llama 3.2 Instruct 11B (Vision)MetaQuality Score 13.5Value Score not available
- Mistral 7B InstructMistralQuality Score 12.6Value Score not available
- Qwen3 30B A3B (Non-reasoning)AlibabaQuality Score 13.6Value Score not available
- Ministral 3 3BMistralQuality Score 12.7Value Score 12.1
- Qwen3 14B (Non-reasoning)AlibabaQuality Score 13.5Value Score not available