CekuraBench
Book a demo

LiveKit vs Smallest AI

All comparisonsLeaderboardTest your agent

LiveKit is ahead on repeatable reliability, task completion, infrastructure reliability, tool call accuracy, interruption handling and response time, and Smallest AI on voice tone and clarity.

LiveKit ranked 3 of 10 · Smallest AI ranked 9 of 10

Last updated Methodology by Luis Ojeda

Which to pick

Pick LiveKit for reliability across repeated runs (14.63 points higher), completing the caller's task (0.81 points higher), calls that connect and stay up (2.85 points higher), accurate tool calls (0.09 higher), handling interruptions (0.06 higher) and fast replies (0.13s faster). Pick Smallest AI for how the agent sounds (0.01 higher).

Every metric, side by side

Bars share one scale across all 10 platforms. The place next to each figure is its rank in the field.

Repeatable reliability

Share of the 82 scenarios that passed on all three runs.

LiveKit
70.73%3rd
Smallest AI
56.10%9th

LiveKit, 14.63 points higher

Task completion

Calls where the expected outcome was fully reached.

LiveKit
95.12%4th
Smallest AI
94.31%5th

LiveKit, 0.81 points higher

Infrastructure-clean calls

Calls with no connection, audio or platform failure.

LiveKit
99.19%3rd
Smallest AI
96.34%7th

LiveKit, 2.85 points higher

Tool call accuracy

Mean score for calling the right tool with the right arguments.

LiveKit
4.67/55th
Smallest AI
4.58/56th

LiveKit, 0.09 higher

Voice tone and clarity

Mean score for how clear and natural the agent sounds.

LiveKit
4.36/53rd
Smallest AI
4.37/52nd

Smallest AI, 0.01 higher

Interruption handling

Mean score for yielding and recovering when the caller cuts in.

LiveKit
4.97/54th
Smallest AI
4.91/58th

LiveKit, 0.06 higher

Mean response time

Mean time for the agent to start replying after the caller stops.

LiveKit
2.59s7th
Smallest AI
2.71s8th

LiveKit, 0.13s faster

246 calls per platform: 82 scenarios, 3 runs each.

What each platform ran, and what we saw

LiveKit

Strength
Ranks third on repeatable reliability with 99.19% infrastructure-clean calls.
What can be improved
Consent was collected, but consent_id was omitted from the handoff tool.
STT, LLM and TTS
  • nova-3
  • openai/gpt-4.1
  • sonic-3
Open example All LiveKit calls

Smallest AI

Strength
94.31% task completion across all 246 calls, and 62.71% pass³ on the Appointment suite (37 of 59 scenarios).
What can be improved
Atoms tool parameters cannot be arrays, so Medicare list arguments arrive as comma-separated text; its tool accuracy reads that text as a list. With the standard check it scores 45.12% pass³.
STT, LLM and TTS
  • pulse
  • electron
  • waves_lightning_v3_1_pro (chelsea)
Open example All Smallest AI calls

Related comparisons

LiveKit vs Smallest AI FAQ

  • LiveKit is more reliable, by 14.63 points. LiveKit passed 70.73% of the 82 scenarios on all 3 runs and Smallest AI passed 56.10%. A scenario only counts when every run of it passed.

  • LiveKit starts replying sooner, 0.13s faster. Mean response time is 2.59s for LiveKit and 2.71s for Smallest AI.

  • LiveKit reached the expected outcome on 95.12% of calls and Smallest AI on 94.31%. LiveKit 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.

Test your voice agent the same way.

Cekura runs these simulated calls on your agent and scores every one.

Book a demoStart free