Yoruba Evaluation of Audio AI Models Yoruba Evaluation of Audio AI Models By Gooey.AI, CLEAR Global and the Gates Foundation • 30 Aug 2026 • Gooey.AI/language 0 5 10 15 20 25 30 35 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0 Accuracy Latency Lower is better More accurate Gemini 3.1 Pro — Accuracy 0.606667, Latency 17.16Gemini 3.1 ProMost Accurate Gemini 3.1 Pro + Omni — Accuracy 0.373333, Latency 26.05Gemini 3.1 Pro + Omni Gemini 3.1 Pro + Intron — Accuracy 0.313333, Latency 28.27Gemini 3.1 Pro + Intron GPT 5.6 Sol + Omni — Accuracy 0.453333, Latency 15.8GPT 5.6 Sol + Omni GPT 5.6 Sol + Intron — Accuracy 0.4, Latency 15.88GPT 5.6 Sol + Intron Claude Sonnet 5 + Omni — Accuracy 0.273333, Latency 13.89Claude Sonnet 5 + OmniFastest Claude Sonnet 5 + Intron — Accuracy 0.36, Latency 15.99Claude Sonnet 5 + Intron Kimi K3 + Omni — Accuracy 0.346667, Latency 26.34Kimi K3 + Omni Kimi K3 + Intron — Accuracy 0.393333, Latency 22.13Kimi K3 + Intron DeepSeek V4 + Omni — Accuracy 0.266667, Latency 27.06DeepSeek V4 + Omni DeepSeek V4 + Intron — Accuracy 0.373333, Latency 30.48DeepSeek V4 + Intron Gemini 3.7 Flash + Omni — Accuracy 0.44, Latency 18.96Gemini 3.7 Flash + Omni Gemini 3.7 Flash + Intron — Accuracy 0.413333, Latency 20.1Gemini 3.7 Flash + Intron Gemini 3.1 Pro — Accuracy 0.606667, Latency 17.160 Gemini 3.1 Pro + Omni — Accuracy 0.373333, Latency 26.051 Gemini 3.1 Pro + Intron — Accuracy 0.313333, Latency 28.272 GPT 5.6 Sol + Omni — Accuracy 0.453333, Latency 15.83 GPT 5.6 Sol + Intron — Accuracy 0.4, Latency 15.884 Claude Sonnet 5 + Omni — Accuracy 0.273333, Latency 13.895 Claude Sonnet 5 + Intron — Accuracy 0.36, Latency 15.996 Kimi K3 + Omni — Accuracy 0.346667, Latency 26.347 Kimi K3 + Intron — Accuracy 0.393333, Latency 22.138 DeepSeek V4 + Omni — Accuracy 0.266667, Latency 27.069 DeepSeek V4 + Intron — Accuracy 0.373333, Latency 30.4810 Gemini 3.7 Flash + Omni — Accuracy 0.44, Latency 18.9611 Gemini 3.7 Flash + Intron — Accuracy 0.413333, Latency 20.112 © 2026 Gooey.AI