Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
Model details →NousResearch: Hermes 2 Pro - Llama-3 8B vs OpenAI: GPT-3.5 Turbo (batch)
NousResearch: Hermes 2 Pro - Llama-3 8B and OpenAI: GPT-3.5 Turbo (batch) are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
Model details →Side-by-side comparison
| Capability | NousResearch: Hermes 2 Pro - Llama-3 8B | OpenAI: GPT-3.5 Turbo (batch) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 8K | 16K | 🏆 OpenAI: GPT-3.5 Turbo (batch) |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.14 | $0.25 | 🏆 NousResearch: Hermes 2 Pro - Llama-3 8B |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.14 | $0.75 | 🏆 NousResearch: Hermes 2 Pro - Llama-3 8B |
| Tool / function calling First-class support for emitting structured tool calls. | — | Yes | 🏆 OpenAI: GPT-3.5 Turbo (batch) |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is NousResearch: Hermes 2 Pro - Llama-3 8B better than OpenAI: GPT-3.5 Turbo (batch)?
NousResearch: Hermes 2 Pro - Llama-3 8B and OpenAI: GPT-3.5 Turbo (batch) are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
What's the price difference between NousResearch: Hermes 2 Pro - Llama-3 8B and OpenAI: GPT-3.5 Turbo (batch)?
Input: $0.14 vs $0.25 per 1M tokens. Output: $0.14 vs $0.75 per 1M tokens.
What context windows do NousResearch: Hermes 2 Pro - Llama-3 8B and OpenAI: GPT-3.5 Turbo (batch) support?
NousResearch: Hermes 2 Pro - Llama-3 8B supports up to 8K tokens. OpenAI: GPT-3.5 Turbo (batch) supports up to 16K tokens.
Do both NousResearch: Hermes 2 Pro - Llama-3 8B and OpenAI: GPT-3.5 Turbo (batch) support tool calling?
NousResearch: Hermes 2 Pro - Llama-3 8B: not advertised. OpenAI: GPT-3.5 Turbo (batch): yes.