Llama 2-34B
#240 of 274 scored.
MetaJul 18, 2023Closed
Capabilities Index
Range 94.5–110.2
105.2
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
No independent scores yet.
Epoch AI hasn't run Llama 2-34B yet. Its scores show up here the morning after they do.
Everything else Epoch has for it
- TriviaQA84.6%
- PIQA63.8%
- Winogrande53.4%
- MMLU50.1%
- OpenBookQA44.3%
- GSM8K42.2%
- ARC AI239.3%
- BBH25.5%
On the index
Around it.
Sources