Llama 3-70B
#188 of 274 scored.
MetaApr 18, 2024Open weights
Capabilities Index
Range 116.6–125.8
122.9
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
How it scores.
- GPQA Diamond20.8%
157th of 186
- Mock AIME4.2%
154th of 176
Everything else Epoch has for it
- MMLU72.4%
- Winogrande67.0%
- DTBench23.6%
- MATH level 522.6%
- Cybench5.0%
On the index
Around it.
Sources