(25Qs) Kikuyu Audio to Text Benchmark | GPT5.1, Gemini 3 Pro, Sunbird v2 & Omnilingual

(25 Qs Updated December 2025)

This page shows a test of many Kikuyu speech‑to‑text and Kikuyu→English systems.
evalinfo

We use the same Kikuyu audio for every system. Then we compare each system’s text to a reference answer and give it a score between 0 and 1.
A higher score means the system is closer to the reference text and usually more accurate.

Ranking Table

#WorkflowAccuracy (Mean)Median Latency (s)
0GPT‑Realtime0.055.06
1SunbirdV2 + Goog MT + Gem3Pro0.7812.38
2SunbirdV2 + GPT5.10.574.85
3SunbirdV2 + Gem3Pro0.8311.96
4Omni + Gem3pro0.7813.84
5Omni + Goog MT + Gem3Pro0.7412.75
6Omni + GPT5.10.189.73
7Gemini 3 Pro0.8112.02
8Gemini 3 Flash0.387.80
9SunbirdV2 + Gem3Flash0.757.23
10Meta MMS + GPT4.1 + GhanaNLP MT0.563.69

You can use this page 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
Gooey Workflows
Input Data Spreadsheet
Loading...
Input Columns

Loading...



Evaluation Workflows


Run cost = 1 credits

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

API: Compare Output Text (from input_audio) Download

Loading...


Aggregate:Mean

Loading...

Loading...


API: Compare Run Time (Median) Download

Loading...


Aggregate:Median

Loading...

Loading...