Llama 3.1 70B
Open SourceOpen SourceAPI Available
Benchmark Scores
77.9/100MMLU82
HumanEval80.5
Math68
Reasoning79
Coding80
About Llama 3.1 70B
Llama 3.1 70B was Meta's workhorse open-source model with a 128K context window. It built a massive ecosystem of fine-tunes and deployments, though Llama 3.3 70B now offers better performance.
Strengths
- +Widely adopted open model
- +Large ecosystem
- +Good fine-tuning base
- +128K context
Weaknesses
- -Superseded by Llama 3.3
- -Less efficient than newer models
Pricing
Per 1M tokens
Input$0.18
Output$0.18
Quick Facts
- Context Window
- 128K
- Parameters
- 70B
- Release Date
- 2024-07-23
- Category
- Open Source
Compare Models
See how Llama 3.1 70B stacks up against other models