Igbo Evaluation of Audio AI Models Igbo 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 0.52, Latency 29.26Gemini 3.1 Pro Gemini 3.1 Pro + Omni — Accuracy 0.37, Latency 28.43Gemini 3.1 Pro + Omni Gemini 3.1 Pro + Intron — Accuracy 0.37, Latency 28.56Gemini 3.1 Pro + Intron GPT 5.6 Sol + Omni — Accuracy 0.51, Latency 14.91GPT 5.6 Sol + OmniFastest GPT 5.6 Sol + Intron — Accuracy 0.52, Latency 17.52GPT 5.6 Sol + Intron Claude Sonnet 5 + Omni — Accuracy 0.35, Latency 15.53Claude Sonnet 5 + Omni Claude Sonnet 5 + Intron — Accuracy 0.41, Latency 16.14Claude Sonnet 5 + Intron Kimi K3 + Omni — Accuracy 0.53, Latency 23.42Kimi K3 + Omni Kimi K3 + Intron — Accuracy 0.55, Latency 23Kimi K3 + IntronMost Accurate DeepSeek V4 + Omni — Accuracy 0.45, Latency 29.05DeepSeek V4 + Omni DeepSeek V4 + Intron — Accuracy 0.35, Latency 28.46DeepSeek V4 + Intron Gemini 3.7 Flash + Omni — Accuracy 0.51, Latency 19.2Gemini 3.7 Flash + Omni Gemini 3.7 Flash + Intron — Accuracy 0.53, Latency 19.72Gemini 3.7 Flash + Intron Gemini 3.1 Pro — Accuracy 0.52, Latency 29.260 Gemini 3.1 Pro + Omni — Accuracy 0.37, Latency 28.431 Gemini 3.1 Pro + Intron — Accuracy 0.37, Latency 28.562 GPT 5.6 Sol + Omni — Accuracy 0.51, Latency 14.913 GPT 5.6 Sol + Intron — Accuracy 0.52, Latency 17.524 Claude Sonnet 5 + Omni — Accuracy 0.35, Latency 15.535 Claude Sonnet 5 + Intron — Accuracy 0.41, Latency 16.146 Kimi K3 + Omni — Accuracy 0.53, Latency 23.427 Kimi K3 + Intron — Accuracy 0.55, Latency 238 DeepSeek V4 + Omni — Accuracy 0.45, Latency 29.059 DeepSeek V4 + Intron — Accuracy 0.35, Latency 28.4610 Gemini 3.7 Flash + Omni — Accuracy 0.51, Latency 19.211 Gemini 3.7 Flash + Intron — Accuracy 0.53, Latency 19.7212 © 2026 Gooey.AI