Llama 3.3 70B
#172 of 274 scored.
MetaDec 6, 2024Open weights
Capabilities Index
Range 121.8–129.7
127.3
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
How it scores.
- GPQA Diamond29.9%
144th of 186
- Mock AIME5.0%
152nd of 176
Everything else Epoch has for it
- MMLU81.7%
- MATH level 541.6%
- Fiction.LiveBench33.3%
- DTBench32.5%
- Balrog23.0%
- LMCA20.6%
- WeirdML14.4%
- SimpleBench3.9%
On the index
Around it.
Sources