PaLM 2-M
#231 of 274 scored.
GoogleMay 17, 2023
Capabilities Index
Range 98.6–116.8
108.3
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
No independent scores yet.
Epoch AI hasn't run PaLM 2-M yet. Its scores show up here the morning after they do.
Everything else Epoch has for it
- TriviaQA81.7%
- HellaSwag78.7%
- Winogrande58.4%
- ARC AI253.2%
- OpenBookQA43.2%
On the index
Around it.
Sources