(25Qs) Kinyarwanda Audio to Text Benchmark | Gemini 3 Pro, GPT‑4o, Mbaza, Sun bird & Omnilingual

(25 Qs Updated 10 Jan 2025)
This page shows a test of many Kinyarwanda speech‑to‑text systems.

For each system, we play the same Kinyarwanda audio and capture its text output.
We then compare that text to a trusted reference answer and give a score between 0 and 1.

A higher score means the system output is closer to the reference text and usually more accurate.

Workflow	Accuracy (mean)	Latency (median)
0 GPT‑Realtime	0.04	5.58
1 Mbza+GPT‑5.1	0.92	3.46
2 Mbaza+Gemini 3 Pro	0.95	8.98
3 Sunbird+GPT‑5.1	0.63	4.28
4 Mbaza+GPT‑5.1+GMT	0.87	3.25
5 Omnilingual+GPT‑5.1	0.84	4.61
6 Omnilingual+Gemini 3 Pro	0.95	9.97
7 Gemini 3 Pro	0.90	9.54
8 Omnilingual+Gemini 3 Flash	0.92	6.06
9 Mbaza+Gemini 3 Flash	0.91	5.04

You can use these scores to:

See which system gets the best score
Compare different models and pipelines side by side
Choose the best system for your app, research, or product
Download all results for deeper analysis

5mo ago

Gooey Workflows

Input Data Spreadsheet

Show as Links

Input Columns

Output Columns

Evaluation Workflows

⚙️ Settings

Run cost = 1 credits

With each run, you agree to Gooey.AI's terms & privacy policy.

Run: Compare Output Text (from input_audio) Download

Aggregate:Mean

Run: Compare Run Time (Median) Download

Aggregate:Median

🐞 Debug

🙋🏽‍♀️ Need more help? Join our Discord

(25Qs) Kinyarwanda Audio to Text Benchmark | Gemini 3 Pro, GPT‑4o, Mbaza, Sun bird & Omnilingual

Gooey Workflows

Input Data Spreadsheet

Input Columns

Output Columns

Evaluation Workflows

🛠️ Developer Tools and Functions

Aggregate:Mean

Aggregate:Median

GET STARTED

LEARN

DEVELOPERS

SOCIAL

CONNECT

EXTRAS