Nous ResearchHermes 4 - Llama-3.1 405B (Reasoning)
- Released
- Aug 27, 2025
- Tracked since
- 2026-07-23
Intelligence index7.5Ranks 473 of 664 models with this metric
Coding index—Not tested
Agentic index—Not tested
Capability profile
5 axes vs. site averageHermes 4 - Llama-3.1 405B (Reasoning)
Site average
Some dimensions have no data yet — marked on the chart
Pricing
per 1M tokens- Input
- $1.00
- Output
- $3.00
Performance
- Output throughput
- 42 tokens/sec
- Time to first token
- 2.37s
- First answer token
- 50.05s
- End-to-end response
- 61.97s
History
2Intelligence index
9→7.5
Output
Unchanged across 62 days of records
Output throughput
35→42
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Gemma 4 E4B (Reasoning)
GoogleIntelligence 8.9$0.100−97% - Gemma 4 E4B (Non-reasoning)GoogleIntelligence 7.5$0.100−97%
- Granite 4.2 3B
IBMIntelligence 9.1$0.120−96% - Qwen3.5 4B (Reasoning)
AlibabaIntelligence 13.1$0.150−95% - Qwen3.5 4B (Non-reasoning)AlibabaIntelligence 10.8$0.150−95%