Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
Official provider results

Sonic 3.6 launch evaluation

Cartesia’s August 27, 2026 launch post reports independent controlled-voice Elo ratings, blind preference win rates against Eleven v3, response latency, and locale coverage for Sonic 3.6.

Source snapshots refreshed
Five measurement lanesVOICE / S2S

Reasoning, task completion, conversation dynamics, experience, and latency stay separate.

Back to directory

Benchmark profile

Scope
independent controlled-voice Elo versus Sonic 3.5 and Eleven v3, blind head-to-head listener preference by locale, reply latency, and locale count
Primary metric
Elo rating and preference win rate (higher is better)
Owner
Cartesia
Available evidence
Exact figures published in the official launch post

What it measures

Voice experience
Is the exchange natural, robust, and responsive?
Latency
How long do responses, tool calls, and full tasks take?

Available results

Independent controlled-voice Elo
1120
#1 at launch

Sonic 3.5 scored 1095 and ElevenLabs Eleven v3 1066.

US English preference vs Eleven v3
92%
Provider-run blind test

UK English 72%, Australian English 77%, French 86%, Spain Spanish 91%.

Reply latency
Under 90 ms
Provider-reported

Generates about 132 characters per second, nearly 2x v3 Conversational.

Locales
61
Documented

11 Indic locales; Odia and Urdu launch above 96% transcript accuracy.

Interpretation limit

Provider-reported results; the Elo figures are Cartesia’s citation of an independent speech leaderboard at launch and the preference tests are Cartesia-run.