Phi-1.5
#265 of 274 scored.
MicrosoftSep 11, 2023Open weights
Capabilities Index
Range 71.6–100.8
91.5
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
No independent scores yet.
Epoch AI hasn't run Phi-1.5 yet. Its scores show up here the morning after they do.
Everything else Epoch has for it
- Winogrande46.8%
- HellaSwag30.1%
- ARC AI225.9%
- MMLU16.8%
- OpenBookQA16.3%
On the index
Around it.
Sources