The highly anticipated 400B class of Llama3 is here! Clocking in at 128k context with impressive eval scores, the Meta AI team continues to push the frontier of open-source LLMs. Meta's latest class of model (Llama 3.1) launched with a var…
Model details →Meta: Llama 3.1 405B Instruct vs OpenAI: GPT-3.5 Turbo (older v0613)
OpenAI: GPT-3.5 Turbo (older v0613) wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
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 | Meta: Llama 3.1 405B Instruct | OpenAI: GPT-3.5 Turbo (older v0613) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 131K | 4K | 🏆 Meta: Llama 3.1 405B Instruct |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $4.00 | $1.00 | 🏆 OpenAI: GPT-3.5 Turbo (older v0613) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $4.00 | $2.00 | 🏆 OpenAI: GPT-3.5 Turbo (older v0613) |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Meta: Llama 3.1 405B Instruct better than OpenAI: GPT-3.5 Turbo (older v0613)?
OpenAI: GPT-3.5 Turbo (older v0613) wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Meta: Llama 3.1 405B Instruct and OpenAI: GPT-3.5 Turbo (older v0613)?
Input: $4.00 vs $1.00 per 1M tokens. Output: $4.00 vs $2.00 per 1M tokens.
What context windows do Meta: Llama 3.1 405B Instruct and OpenAI: GPT-3.5 Turbo (older v0613) support?
Meta: Llama 3.1 405B Instruct supports up to 131K tokens. OpenAI: GPT-3.5 Turbo (older v0613) supports up to 4K tokens.
Do both Meta: Llama 3.1 405B Instruct and OpenAI: GPT-3.5 Turbo (older v0613) support tool calling?
Meta: Llama 3.1 405B Instruct: yes. OpenAI: GPT-3.5 Turbo (older v0613): yes.