Nigerian Pidgin Evaluation of Audio AI Models
Nigerian Pidgin 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 0.65, Latency 16.29
Gemini 3.1 Pro
Gemini 3.1 Pro + Omni — Accuracy 0.63, Latency 27.21
Gemini 3.1 Pro + Omni
Gemini 3.1 Pro + Intron — Accuracy 0.66, Latency 32.48
Gemini 3.1 Pro + Intron
GPT 5.6 Sol + Omni — Accuracy 0.68, Latency 17.05
GPT 5.6 Sol + Omni
GPT 5.6 Sol + Intron — Accuracy 0.67, Latency 18.39
GPT 5.6 Sol + Intron
Claude Sonnet 5 + Omni — Accuracy 0.62, Latency 16.18
Claude Sonnet 5 + Omni
Fastest
Claude Sonnet 5 + Intron — Accuracy 0.63, Latency 20.8
Claude Sonnet 5 + Intron
Kimi K3 + Omni — Accuracy 0.71, Latency 18.83
Kimi K3 + Omni
Kimi K3 + Intron — Accuracy 0.75, Latency 22.22
Kimi K3 + Intron
Most Accurate
DeepSeek V4 + Omni — Accuracy 0.56, Latency 26.36
DeepSeek V4 + Omni
DeepSeek V4 + Intron — Accuracy 0.63, Latency 28.26
DeepSeek V4 + Intron
Gemini 3.7 Flash + Omni — Accuracy 0.67, Latency 26.18
Gemini 3.7 Flash + Omni
Gemini 3.7 Flash + Intron — Accuracy 0.67, Latency 24.93
Gemini 3.7 Flash + Intron
Gemini 3.1 Pro — Accuracy 0.65, Latency 16.29
0
Gemini 3.1 Pro + Omni — Accuracy 0.63, Latency 27.21
1
Gemini 3.1 Pro + Intron — Accuracy 0.66, Latency 32.48
2
GPT 5.6 Sol + Omni — Accuracy 0.68, Latency 17.05
3
GPT 5.6 Sol + Intron — Accuracy 0.67, Latency 18.39
4
Claude Sonnet 5 + Omni — Accuracy 0.62, Latency 16.18
5
Claude Sonnet 5 + Intron — Accuracy 0.63, Latency 20.8
6
Kimi K3 + Omni — Accuracy 0.71, Latency 18.83
7
Kimi K3 + Intron — Accuracy 0.75, Latency 22.22
8
DeepSeek V4 + Omni — Accuracy 0.56, Latency 26.36
9
DeepSeek V4 + Intron — Accuracy 0.63, Latency 28.26
10
Gemini 3.7 Flash + Omni — Accuracy 0.67, Latency 26.18
11
Gemini 3.7 Flash + Intron — Accuracy 0.67, Latency 24.93
12
© 2026
Gooey.AI