Hausa Evaluation of Audio AI Models Hausa 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 0.71, Latency 16.33Gemini 3.1 ProMost Accurate Gemini 3.1 Pro + Omni — Accuracy 0.38, Latency 26.8Gemini 3.1 Pro + Omni Gemini 3.1 Pro + Intron — Accuracy 0.43, Latency 29.84Gemini 3.1 Pro + Intron GPT 5.6 Sol + Omni — Accuracy 0.59, Latency 14.36GPT 5.6 Sol + Omni GPT 5.6 Sol + Intron — Accuracy 0.59, Latency 18.13GPT 5.6 Sol + Intron Claude Sonnet 5 + Omni — Accuracy 0.5, Latency 13.63Claude Sonnet 5 + OmniFastest Claude Sonnet 5 + Intron — Accuracy 0.39, Latency 15.05Claude Sonnet 5 + Intron Kimi K3 + Omni — Accuracy 0.63, Latency 20.82Kimi K3 + Omni Kimi K3 + Intron — Accuracy 0.56, Latency 24.13Kimi K3 + Intron DeepSeek V4 + Omni — Accuracy 0.47, Latency 29.62DeepSeek V4 + Omni DeepSeek V4 + Intron — Accuracy 0.39, Latency 32.93DeepSeek V4 + Intron Gemini 3.7 Flash + Omni — Accuracy 0.51, Latency 17.21Gemini 3.7 Flash + Omni Gemini 3.7 Flash + Intron — Accuracy 0.54, Latency 20.41Gemini 3.7 Flash + Intron Gemini 3.1 Pro — Accuracy 0.71, Latency 16.330 Gemini 3.1 Pro + Omni — Accuracy 0.38, Latency 26.81 Gemini 3.1 Pro + Intron — Accuracy 0.43, Latency 29.842 GPT 5.6 Sol + Omni — Accuracy 0.59, Latency 14.363 GPT 5.6 Sol + Intron — Accuracy 0.59, Latency 18.134 Claude Sonnet 5 + Omni — Accuracy 0.5, Latency 13.635 Claude Sonnet 5 + Intron — Accuracy 0.39, Latency 15.056 Kimi K3 + Omni — Accuracy 0.63, Latency 20.827 Kimi K3 + Intron — Accuracy 0.56, Latency 24.138 DeepSeek V4 + Omni — Accuracy 0.47, Latency 29.629 DeepSeek V4 + Intron — Accuracy 0.39, Latency 32.9310 Gemini 3.7 Flash + Omni — Accuracy 0.51, Latency 17.2111 Gemini 3.7 Flash + Intron — Accuracy 0.54, Latency 20.4112 © 2026 Gooey.AI