Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long co…
Model details →Nous: Hermes 3 70B Instruct vs OpenAI: GPT-4o (2024-11-20)
Nous: Hermes 3 70B Instruct wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...
Model details →Side-by-side comparison
| Capability | Nous: Hermes 3 70B Instruct | OpenAI: GPT-4o (2024-11-20) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 131K | 128K | 🏆 Nous: Hermes 3 70B Instruct |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.70 | $2.50 | 🏆 Nous: Hermes 3 70B Instruct |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.70 | $10.00 | 🏆 Nous: Hermes 3 70B Instruct |
| Tool / function calling First-class support for emitting structured tool calls. | — | Yes | 🏆 OpenAI: GPT-4o (2024-11-20) |
| Vision input Accepts image inputs alongside text. | — | Yes | 🏆 OpenAI: GPT-4o (2024-11-20) |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Nous: Hermes 3 70B Instruct better than OpenAI: GPT-4o (2024-11-20)?
Nous: Hermes 3 70B Instruct wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Nous: Hermes 3 70B Instruct and OpenAI: GPT-4o (2024-11-20)?
Input: $0.70 vs $2.50 per 1M tokens. Output: $0.70 vs $10.00 per 1M tokens.
What context windows do Nous: Hermes 3 70B Instruct and OpenAI: GPT-4o (2024-11-20) support?
Nous: Hermes 3 70B Instruct supports up to 131K tokens. OpenAI: GPT-4o (2024-11-20) supports up to 128K tokens.
Do both Nous: Hermes 3 70B Instruct and OpenAI: GPT-4o (2024-11-20) support tool calling?
Nous: Hermes 3 70B Instruct: not advertised. OpenAI: GPT-4o (2024-11-20): yes.
Compare Nous: Hermes 3 70B Instruct with other models
vs Anthropic Claude Haiku Latestvs Anthropic Claude Sonnet Latestvs Anthropic: Claude Fable Latestvs Anthropic: Claude Opus Latest