Fun-Audio-Chat Technical Report

Open paper
Benchmark Model Rank Results
audio-question-answering-on-openaudiobench-llamaquestionsFun-Audio-Chat-30B-A3B#1Accuracy: 85.00
audio-understanding-reasoning-on-mmsuFun-Audio-Chat-30B-A3B#6Accuracy: 70.1

Rank counts only results with a code link.