Falcon-7B
#256 of 274 scored.
TIIApr 24, 2023Open weights
Capabilities Index
Range 81.1–102.4
95.1
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
No independent scores yet.
Epoch AI hasn't run Falcon-7B yet. Its scores show up here the morning after they do.
Everything else Epoch has for it
- LAMBADA74.9%
- HellaSwag70.8%
- TriviaQA64.6%
- PIQA60.6%
- OpenBookQA35.5%
- Winogrande34.4%
- ARC AI230.5%
- MMLU13.3%
- GSM8K6.8%
- BBH5.0%
On the index
Around it.
Sources