Nous Research
Hermes 4 - Llama-3.1 70B (Reasoning)
Quality Score15.1
Value Score13.9
Reliability25.3
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 128k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.130
- Output
- $0.400
- Cached Input
- not available
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 9.9
- Coding
- not available
- Agentic
- not available
- Omniscience
- -49.4
- Correct
- 23.5%
- Blended price
- $0.157
Answer outcomes
Correct 23.5%Incorrect 72.9%Abstained 3.5%
Artificial Analysis benchmarks
- SciCode
- 34%
- Humanity’s Last Exam
- 9%
- GPQA Diamond
- 70%
- CritPt
- 0%
- AA-Omniscience
- 25%
- AA-LCR
- 8%
Similar models
- Hermes 4 - Llama-3.1 405B (Reasoning)Nous ResearchQuality Score 19.8Value Score 11.9
- Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous ResearchQuality Score 18.7Value Score 11.1
- Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous ResearchQuality Score 12.0Value Score 10.2
- DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous ResearchQuality Score not availableValue Score not available
- DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous ResearchQuality Score not availableValue Score not available
- Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIAQuality Score 14.1Value Score 10.5