Artificial Analysis average word error rate

In use

Speech transcription systems are scored by average word error rate across the Artificial Analysis evaluation set.

Google quotes Artificial Analysis average WER for Gemini 3.5 Transcribe. The almanac records only the values quoted in Google's launch post.

Model scored in lab cards

Launch post lists it, from 1 lab

Gemini 3.5 Transcribe leads with 4.00%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Bars Table

Source: Labs’ model cards

#	Model	Score	Setting	Date	Source
1	Gemini 3.5 Transcribe	4.00%		Aug 2026	Lab model card

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card

Source: Labs’ model cards

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Google DeepMind

Date	Launch post	Score	As the post writes it
Aug 26, 2026	Gemini 3.5 Transcribe	4	Average Word Error Rate (WER), streaming, Artificial Analysis