LLaMA-65B
#227 of 274 scored.
MetaFeb 24, 2023Open weights
Capabilities Index
Range 101.4–114.1
110.2
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
No independent scores yet.
Epoch AI hasn't run LLaMA-65B yet. Its scores show up here the morning after they do.
Everything else Epoch has for it
- TriviaQA86.0%
- HellaSwag78.9%
- LAMBADA77.7%
- PIQA65.6%
- ARC AI259.3%
- GSM8K54.4%
- Winogrande54.0%
- MMLU51.2%
- OpenBookQA46.9%
- BBH44.5%
On the index
Around it.
Sources