AssemblyAI's benchmark found small models close to larger ones on short calls, but less reliable on longer meetings and harder extraction tasks. (Read More)
Small LLMs stay competitive on short transcripts, then fade at meeting length
6 days ago
5
AssemblyAI's benchmark found small models close to larger ones on short calls, but less reliable on longer meetings and harder extraction tasks. (Read More)
Bengali (Bangladesh) · 
English (United States) ·