Gemini Live
- Strength
- Second-highest repetition score at 4.78/5 across 174 scored calls.
- What can be improved
- One rerun had no latency evidence and scored 0/5 for both task outcome and tool accuracy.
- reasoning: high
- hybrid VAD
Retell is ahead of Gemini Live on repeatable reliability, task completion, infrastructure reliability, tool call accuracy, interruption handling and response time.
Last updated Methodology by Luis Ojeda
Retell is the better pick over Gemini Live on every measure that separates them: reliability across repeated runs (45.12 points higher), completing the caller's task (6.08 points higher), calls that connect and stay up (26.01 points higher), accurate tool calls (0.44 higher), handling interruptions (0.03 higher) and fast replies (0.84s faster).
Bars share one scale across all 8 platforms. The place next to each figure is its rank in the field.
Share of the 82 scenarios that passed on all three runs.
Retell, 45.12 points higher
Calls where the expected outcome was fully reached.
Retell, 6.08 points higher
Calls with no connection, audio or platform failure.
Retell, 26.01 points higher
Mean score for calling the right tool with the right arguments.
Retell, 0.44 higher
Mean score for how clear and natural the agent sounds.
Not comparable
Mean score for yielding and recovering when the caller cuts in.
Retell, 0.03 higher
Mean time for the agent to start replying after the caller stops.
Retell, 0.84s faster
246 calls per platform: 82 scenarios, 3 runs each.
Retell is more reliable, by 45.12 points. Gemini Live passed 30.49% of the 82 scenarios on all 3 runs and Retell passed 75.61%. A scenario only counts when every run of it passed.
Retell starts replying sooner, 0.84s faster. Mean response time is 3.05s for Gemini Live and 2.21s for Retell.
Gemini Live reached the expected outcome on 87.80% of calls and Retell on 93.88%. Retell is ahead on task completion.
Both ran the same Appointment and Medicare agents through the same 82 caller scenarios, 3 times each, with the same evaluators and mock tools. Only the platform and its speech and model components changed.