A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge the model - [mergek…
Model details →Goliath 120B vs Cohere: Command A
Cohere: Command A wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary and open-weights models Command A…
Model details →Side-by-side comparison
| Capability | Goliath 120B | Cohere: Command A | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 6K | 256K | 🏆 Cohere: Command A |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $3.75 | $2.50 | 🏆 Cohere: Command A |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $7.50 | $10.00 | 🏆 Goliath 120B |
| Tool / function calling First-class support for emitting structured tool calls. | — | — | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Goliath 120B better than Cohere: Command A?
Cohere: Command A wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Goliath 120B and Cohere: Command A?
Input: $3.75 vs $2.50 per 1M tokens. Output: $7.50 vs $10.00 per 1M tokens.
What context windows do Goliath 120B and Cohere: Command A support?
Goliath 120B supports up to 6K tokens. Cohere: Command A supports up to 256K tokens.
Do both Goliath 120B and Cohere: Command A support tool calling?
Goliath 120B: not advertised. Cohere: Command A: not advertised.