Share this page
-
DoomBench assesses “Meta releases frontier-scale Llama 3.1 open models” as evidence moving toward doom, with magnitude 82 and confidence 99 out of 100 in the capability gains category.
-
The DoomBench assessment of “Meta releases frontier-scale Llama 3.1 open models” is based on reporting from Meta and records the editorial rationale, source quality, attribution, and revision history.
-
DoomBench summarizes “Meta releases frontier-scale Llama 3.1 open models” as follows: Meta released Llama 3.1 in 8B, 70B and 405B base and instruction tiers with 128K context, multilingual support, tool use, downloadable weights and...
https://www.doombench.com/news/meta-releases-frontier-scale-llama-3-1-open-models-2024-07-23