5models tracked · ranked by intelligence, speed & price
Nous's smartest model is Hermes 4 405B (18.6 on the Intelligence Index), its fastest is Hermes 4 70B at 65 tokens/sec, and its cheapest is Hermes 4 70B at $0.130 per million input tokens. All 5 Nous models are compared below by intelligence, speed, latency, context and price.
| Model | Intel | Speed | Latency | In $/M | Context |
|---|---|---|---|---|---|
| hermes-4-405b ReasoningJSON | 18.6 | 32 | 465ms | $1.00 | 131K |
| hermes-3-llama-3.1-405b:free | 17.6 | 21 | 376ms | Free | 131K |
| hermes-3-llama-3.1-405b JSON | 17.6 | 21 | 391ms | $1.00 | 131K |
| hermes-4-70b ReasoningJSON | 16.0 | 65 | 275ms | $0.130 | 131K |
| hermes-3-llama-3.1-70b JSON | — | 25 | 334ms | $0.700 | 131K |