Llama 3.2 90B
#182 of 274 scored.
MetaSep 24, 2024Open weights
Capabilities Index
Range 119.4–127.3
125.5
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
How it scores.
- GPQA Diamond21.4%
154th of 186
- Mock AIME2.5%
158th of 176
Everything else Epoch has for it
- MMLU73.7%
- GeoBench52.0%
- MATH level 539.4%
- Balrog27.3%
On the index
Around it.
Sources