Gemini 3.8 Live Extended Thinking vs Amazon Nova 2 Sonic

Gemini 3.8 Live Extended Thinking is more reliable, by 12.9 points. Gemini 3.8 Live Extended Thinking handled 17 of 70 real callers well on all three runs, and Amazon Nova 2 Sonic 8. A caller only counts when every run of the call scored 80 or more.

For a voice agent, Gemini 3.8 Live Extended Thinking, since it handles more real callers well on every run. Gemini 3.8 Live Extended Thinking is ahead on ELO rating, hearing score, turn taking score, speaking score, task handling score, reliability, calls handled well, calls fully resolved and median latency, and Amazon Nova 2 Sonic on calls where the agent went quiet.

Gemini 3.8 Live Extended Thinking, by 9.0 points higher. Gemini 3.8 Live Extended Thinking fully resolved 22.9% of calls and Amazon Nova 2 Sonic 13.8%. A call counts only when every step the caller needed was done.

Yes. Gemini 3.8 Live Extended Thinking starts replying 0.66s sooner at the median. Gemini 3.8 Live Extended Thinking takes 2.10s at the median and 2.60s at p90; Amazon Nova 2 Sonic takes 2.76s and 3.40s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

Amazon Nova 2 Sonic, by 10.5 points. The agent went quiet for 10 seconds or more on 17.6% of Gemini 3.8 Live Extended Thinking calls and 7.1% of Amazon Nova 2 Sonic calls.

There is no verified per-minute rate for Gemini 3.8 Live Extended Thinking and Amazon Nova 2 Sonic, so cost cannot be compared yet.

Cekura ran both as the whole agent with the same prompt, tools and phone connection. Both took the same 70 recorded real human callers on live calls, three times each. Each call is graded on 25 skills across Hearing, Turn Taking, Task Handling and Speaking, and passes at a score of 80 out of 100.