Llama 3.1-70B
#180 of 274 scored.
MetaJul 23, 2024Open weights
Capabilities Index
Range 120.0–128.5
125.9
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
How it scores.
- GPQA Diamond25.6%
152nd of 186
- Mock AIME3.5%
157th of 176
Everything else Epoch has for it
- MMLU73.5%
- MATH level 536.7%
- DTBench33.3%
- Balrog27.9%
- LMCA17.5%
- WeirdML9.0%
- The Agent Company6.9%
On the index
Around it.
Sources