ai-performance-evaluation

Jun
08
Qwen2 72b BEATS LLaMA3 70b - Fully Tested (0.5b not good)

Qwen2 72b BEATS LLaMA3 70b - Fully Tested (0.5b not good)

🆕 from Matthew Berman! Discover how Qwen2 72b outperforms LLaMA3 70b in various evaluations, showcasing superior performance in code and math
3 min read