Llama 3.1-405B
#167 of 274 scored.
MetaJul 23, 2024Open weights
Capabilities Index
Range 123.8–130.8
128.8
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
How it scores.
- GPQA Diamond34.5%
132nd of 186
- Mock AIME9.6%
135th of 176
Everything else Epoch has for it
- ARC AI293.7%
- HellaSwag85.6%
- TriviaQA82.7%
- MMLU79.3%
- Winogrande78.4%
- BBH77.2%
- PIQA71.8%
- MATH level 549.8%
- DTBench35.6%
- WeirdML21.4%
- SimpleBench7.6%
- Cybench7.5%
- The Agent Company7.4%
On the index
Around it.
Sources