PolyAI Dialog-RSN-1 vs Cascade

Compare
PolyAI Dialog-RSN-1PolyAI
Wins 2 of 8
Reliability
64.6%
Response time
1.36s
Cost / min
$0.0406
CascadeBaseline, not ranked
Wins 5 of 8
Reliability
82.9%
Response time
2.17s
Cost / min
n/a

Cascade is ahead on reliability, success rate, agent responses, data accuracy and interruption, and PolyAI Dialog-RSN-1 on calls where the agent went quiet and response time.

Last updated Methodology by Dileep Chagam

Who is better at what

PolyAI Dialog-RSN-1Cascade
  • Reliability64.6%82.9%
  • Success rate67.9%93.1%
  • Agent responses93.1%99.2%
  • Data accuracy73.0%94.1%
  • Went quiet0.0%0.8%
  • Interruption4.854.96
  • Response time1.36s2.17s
  • Cost / min$0.0406No verified rate

Reliability on booking and Medicare calls

Scenarios the agent passed on every one of its 3 runs.

Booking callsMedicare calls
  1. 93%
    57%
    Cascade
  2. 86%
    9%
    Dialog-RSN-1

Dialog-RSN-1 vs Cascade FAQ

  • Cascade is more reliable, by 18.3 points. PolyAI Dialog-RSN-1 passed 53 of 82 scenarios on all three runs, and Cascade passed 68. A scenario only counts when every run of it passed.

  • On reliability, no: the cascade passes more scenarios on every run. Cascade is ahead on reliability, success rate, agent responses, data accuracy and interruption, and PolyAI Dialog-RSN-1 on calls where the agent went quiet and response time. Both ran as the same agent, with the same prompt and tools.

  • Cascade, by 21.1 points. PolyAI Dialog-RSN-1 saved everything exactly right on 73.0% of the calls that save data, and Cascade on 94.1%. On Booking calls, 97.7% against 98.8%. On Medicare calls, 9.1% against 81.8%. A call counts only when nothing is missing, wrong, extra or saved twice.

  • Yes. PolyAI Dialog-RSN-1 starts replying 0.81s sooner at the median. PolyAI Dialog-RSN-1 takes 1.36s at the median and 1.87s at p90; Cascade takes 2.17s and 2.51s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

  • Cascade, by 0.11 on a 0 to 5 scale. PolyAI Dialog-RSN-1 scores 4.85 and Cascade 4.96 for how well the agent handled being talked over.

  • PolyAI Dialog-RSN-1, by 0.8 points. The agent went quiet for 10 seconds or more on 0.0% of PolyAI Dialog-RSN-1 calls and 0.8% of Cascade calls.

  • There is no verified per-minute rate for Cascade, so cost cannot be compared yet.

  • Cekura ran both as the whole agent in the same open-source Pipecat pipeline, with the same prompt, tools and connection. A simulated caller worked through all 82 scenarios on live calls, three times each, 3,936 calls across the benchmark. A call passes only when the agent said the right things and saved the right data. The cascade runs the same agent for reference and is never ranked.

Test your voice agent the same way.

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