PolyAI is ahead on repeatable reliability, task completion, tool call accuracy and interruption handling, and Telnyx on infrastructure reliability, voice tone and clarity and response time.
Last updated Methodology by Luis Ojeda
Pick PolyAI for reliability across repeated runs (19.51 points higher), completing the caller's task (1.22 points higher), accurate tool calls (0.19 higher) and handling interruptions (0.36 higher). Pick Telnyx for calls that connect and stay up (0.81 points higher), how the agent sounds (0.24 higher) and fast replies (0.65s faster).
Bars share one scale across all 10 platforms. The place next to each figure is its rank in the field.
Share of the 82 scenarios that passed on all three runs.
PolyAI, 19.51 points higher
Calls where the expected outcome was fully reached.
PolyAI, 1.22 points higher
Calls with no connection, audio or platform failure.
Telnyx, 0.81 points higher
Mean score for calling the right tool with the right arguments.
PolyAI, 0.19 higher
Mean score for how clear and natural the agent sounds.
Telnyx, 0.24 higher
Mean score for yielding and recovering when the caller cuts in.
PolyAI, 0.36 higher
Mean time for the agent to start replying after the caller stops.
Telnyx, 0.65s faster
246 calls per platform: 82 scenarios, 3 runs each.
PolyAI is more reliable, by 19.51 points. PolyAI passed 87.80% of the 82 scenarios on all 3 runs and Telnyx passed 68.29%. A scenario only counts when every run of it passed.
PolyAI is more reliable, by 19.51 points. PolyAI passed 87.80% of the 82 scenarios on all 3 runs and Telnyx passed 68.29%. A scenario only counts when every run of it passed.
Telnyx starts replying sooner, 0.65s faster. Mean response time is 2.46s for PolyAI and 1.82s for Telnyx.
PolyAI reached the expected outcome on 98.78% of calls and Telnyx on 97.56%. PolyAI 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.
Cekura runs these simulated calls on your agent and scores every one.
