Llama 2 Chat 70B vs LLaMA 3.1 (405B): Benchmarks, Pricing, and Context Window Comparison
Llama 2 Chat 70B vs LLaMA 3.1 (405B) compares provider, context window, token pricing, benchmark performance, and release timeline in one side-by-side view. Use this page to quickly identify which model is a better fit for your production constraints, quality targets, and estimated cost per request.
Verdict
Llama 2 Chat 70B has lower listed token pricing, while LLaMA 3.1 (405B) can still be preferable if benchmark results better match your workload.
Author: Mirai Minds Research Team
Last updated:
Compare
to
Overview
Llama 2 Chat 70B was released 12 months before LLaMA 3.1 (405B).
| Llama 2 Chat 70B | LLaMA 3.1 (405B) | |
|---|---|---|
Provider The entity that provides this model. | Meta | Meta |
Input Context Window The number of tokens supported by the input context window. | 4,096 tokens | 128K tokens |
Maximum Output Tokens The number of tokens that can be generated by the model in a single request. | 2,048 tokens | 2,048 tokens |
Release Date When the model was first released. | Jul 18, 2023 over 1 yearago 2023-07-18 | Jul 23, 2024 over 1 year 2024-07-23 |
Leaderboard
| Llama 2 Chat 70B | LLaMA 3.1 (405B) | |
|---|---|---|
Rank | 41 | Unknown |
Arena Elo | 1088 | Not specified. |
95% CI | +3/-4 | Not specified. |
Votes | 38748 | Not specified. |
License | Llama 2 Community | Not specified. |
Knowledge Cutoff | 7/2023 7/2023 | Unknown |
Pricing
| Llama 2 Chat 70B | LLaMA 3.1 (405B) | |
|---|---|---|
Input Cost of input data provided to the model. | $0.65 per million tokens | $1.79 per million tokens |
Output Cost of output tokens generated by the model. | $2.75 per million tokens | $1.79 per million tokens |
Benchmarks
Compare relevant benchmarks between Llama 2 Chat 70B and LLaMA 3.1 (405B) Instruct.
| Llama 2 Chat 70B | LLaMA 3.1 (405B) | |
|---|---|---|
MMLU Evaluating LLM knowledge acquisition in zero-shot and few-shot settings. | 68.9 (5-shot) | 85.2 (5-shot) |
MMMU A wide ranging multi-discipline and multimodal benchmark. | 30.1 | Benchmark not available. |
HellaSwag A challenging sentence completion benchmark. | Benchmark not available. | Benchmark not available. |