Skip to main content

OpenAIGoogleAudio matchupSpeech to text

GPT-4o Mini Transcribevs.Gemini 3.5 Transcribe

Which model is better?

Gemini 3.5 Transcribe is slightly ahead in independent tests, but the lead is not certain.

Independent tests
GPT-4o Mini Transcribe0 of 1
Gemini 3.5 Transcribe0 of 1
Artificial Analysis
Popularity
GPT-4o Mini Transcribe33
Gemini 3.5 Transcribeahead52
out of 100
Weights and access
GPT-4o Mini Transcribeproprietary
Gemini 3.5 Transcribeproprietary
Price
GPT-4o Mini Transcribe$1.25 per 1M audio tokens
Gemini 3.5 Transcribe$2 per 1M audio tokens ($0.003 per audio minute)
verbatim from the provider

Pick GPT-4o Mini Transcribe for

No clear edge

Pick Gemini 3.5 Transcribe for

leaning Artificial Analysismore popular

Shared tests

Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.

Artificial Analysis

Gemini 3.5 Transcribe slightly ahead

Artificial Analysis AA-WER (non-streaming)

GPT-4o Mini Transcribe4.5 %
Gemini 3.5 Transcribe2.6 %

lower is better, as of October 15, 2026

Source · latest October 15, 2026

All data side by side

Prices are verbatim from the provider, because audio models bill per minute, character or token.

GPT-4o Mini TranscribeGemini 3.5 Transcribe
TaskSpeech to textSpeech to text
DeveloperOpenAIGoogle
StatusDeprecatedActive
Weightsproprietaryproprietary
Runs locallynono
Price$1.25 per 1M audio tokens$2 per 1M audio tokens ($0.003 per audio minute)
Popularity (out of 100)3352