Announcing Gemma 3n preview: powerful, efficient, mobile-first AI
Open paper
Benchmark
Model
Rank
Results
audio-understanding-reasoning-on-mmau
Gemma 3n (4B)
#9
Accuracy (Avg, Test-mini): 58.00
audio-understanding-reasoning-on-mmau
Gemma 3n (2B)
#10
Accuracy (Avg, Test-mini): 51.69
Rank counts only results with a code link.