List your company

Audio Question Answering on Bio-acoustic QA

81.25AccuracySpeech-Hands
40.461251.050661.6472.2294Jan 14, 2026

Evaluation results

MethodLinks
Speech-Handsmode=parallel agentic, sampling=majority sampling2026.0181.2577.37
Qwen2.5-Omnisetting=SFT with official training data2026.0178.1363.13
Qwen2.5-Omnisetting=GRPO with official training data2026.0178.0965.54
Qwen2.5-Omnisetting=GER: => AF3 (cascaded agentic)2026.0176.2968.93
AudioFlamingo 3 (AF3)2026.0171.8874.49
Speech-Handsmode=parallel agentic, setting=SFT with official training data2026.0167.8675.75
Qwen2.5-Omnisetting=GRPO with external audio data2026.0162.3275.1
Qwen2.5-Omni2026.0147.3257.87
Gemini-2-Flash2026.0142.0356.61