Llama 3.1 8B (CoT)

Reported on 2 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology2 results

Transfer LearningonMML
Average (%)· uses extra data· 2024-07-31
73
best: 87 (GPT-4 o1(300b))
The Llama 3 Herd of Models arXiv:2407.21783
Multi-Task LearningonMML
Average (%)· uses extra data· 2024-07-31
73
best: 87 (GPT-4 o1(300b))
The Llama 3 Herd of Models arXiv:2407.21783