Official provider results
Gemini 3.8 Audio model evaluation
Google’s September 15 model evaluation reports separate results for Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking on spoken agent tasks and a speech-to-speech index.
Source snapshots refreshed
Five measurement lanesVOICE / S2S
Reasoning, task completion, conversation dynamics, experience, and latency stay separate.
Benchmark profile
- Scope
- Live API voice-agent evaluations using ServiceNow EVA-Bench, a source-owned speech-to-speech index and τ-Voice, and Sierra τ³-Banking
- Primary metric
- Task success and speech-to-speech index (higher is better)
- Owner
- Google DeepMind
- Available evidence
- Exact bar-chart labels in Google’s model evaluation PDF; EVA-Bench scatterplot points are not tabulated
What it measures
Task completion
Can it follow policy, use tools, and finish a workflow?
Conversation dynamics
Can it handle turns, interruptions, ambiguity, and state?
Voice experience
Is the exchange natural, robust, and responsive?
Available results
- Gemini 3.8 Live speech-to-speech index
- 76.0%
- Gemini 3.8 Live τ-Voice task success
- 30.1%
- Gemini 3.8 Live Extended Thinking speech-to-speech index
- 82.6%
- Gemini 3.8 Live Extended Thinking τ-Voice task success
- 68.6%
- Gemini 3.8 Live Extended Thinking Sierra τ³-Banking
- 35.1%
Source-owned index shown in Google’s September 2026 evaluation PDF.
Google’s comparison chart for the default Live model.
High-effort Extended Thinking run.
High-effort Extended Thinking run; do not attribute this result to the default Live model.
High-effort Live API run on the banking task suite.
Interpretation limit
Google’s PDF combines evaluations run by separate teams using different APIs and effort settings. The Extended Thinking task rows use high effort; the EVA-Bench scatterplot labels are plotted without exact figures. These voice-protocol results do not enter weighted text-model scores, and the plotted audio-hour costs are not canonical API prices.