LLaMA-33B
#236 of 274 scored.
MetaFeb 24, 2023Open weights
Capabilities Index
Range 97.4–112.1
107.4
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
No independent scores yet.
Epoch AI hasn't run LLaMA-33B yet. Its scores show up here the morning after they do.
Everything else Epoch has for it
- TriviaQA83.8%
- LAMBADA77.2%
- HellaSwag77.1%
- PIQA64.6%
- ARC AI256.7%
- Winogrande52.0%
- MMLU44.9%
- OpenBookQA44.8%
- GSM8K44.1%
- BBH33.3%
On the index
Around it.
Sources