Deepslate Opal is ahead on reliability, success rate, agent responses and data accuracy, and GPT Realtime 2.1 Mini on stalled calls, interruption, response time and cost.
Last updated Methodology by Dileep Chagam
Pick Deepslate Opal for reliability across repeated calls (7.3 points higher), calls that pass every check (8.5 points higher), getting the agent's replies right (2.4 points higher) and saving the caller's data correctly (8.0 points higher). Pick GPT Realtime 2.1 Mini for fewer stalled calls (2.8 points lower), handling interruptions (0.03 higher), fast replies (0.19s sooner) and lower cost ($0.092 cheaper).
Scenarios that passed on all three runs.
Deepslate Opal, 7.3 points higher
Calls that passed every check.
Deepslate Opal, 8.5 points higher
Calls where the agent's replies reached the expected outcome.
Deepslate Opal, 2.4 points higher
Calls where everything the agent saved matched exactly.
Deepslate Opal, 8.0 points higher
Calls where the agent went silent for 10 seconds or more.
Realtime 2.1 Mini, 2.8 points lower
How well it handled being talked over, 0 to 5.
Realtime 2.1 Mini, 0.03 higher
Median time to start replying after the caller finishes.
Realtime 2.1 Mini, 0.19s sooner
One minute of call at the vendor's published rates.
Realtime 2.1 Mini, $0.092 cheaper
The small figure is the place among ranked models. The cascade is not ranked.
Realtime 2.1 Mini 2.08s, Deepslate Opal 2.27s at the median.
Deepslate Opal is more reliable, by 7.3 points. Deepslate Opal passed 47 of 82 scenarios on all three runs, and GPT Realtime 2.1 Mini passed 41. A scenario only counts when every run of it passed.
For a phone agent, Deepslate Opal, since it gets more scenarios right on every run. Deepslate Opal is ahead on reliability, success rate, agent responses and data accuracy, and GPT Realtime 2.1 Mini on stalled calls, interruption, response time and cost.
Deepslate Opal, by 8.0 points. Deepslate Opal saved everything exactly right on 72.6% of the calls that save data, and GPT Realtime 2.1 Mini on 64.5%. On Appointments, 85.4% against 88.8%. On Medicare, 39.4% against 0.0%. A call counts only when nothing is missing, wrong, extra or saved twice.
No. GPT Realtime 2.1 Mini starts replying 0.19s sooner at the median. Deepslate Opal takes 2.27s at the median and 2.83s at p90; GPT Realtime 2.1 Mini takes 2.08s and 2.75s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.
GPT Realtime 2.1 Mini, by 0.03 on a 0 to 5 scale. Deepslate Opal scores 4.96 and GPT Realtime 2.1 Mini 4.99 for how well the agent handled being talked over.
GPT Realtime 2.1 Mini, by 2.8 points. The agent went silent for 10 seconds or more on 5.3% of Deepslate Opal calls and 2.5% of GPT Realtime 2.1 Mini calls.
GPT Realtime 2.1 Mini is $0.092 cheaper a minute. Deepslate Opal costs $0.112 a minute of call and GPT Realtime 2.1 Mini $0.020, at each vendor's published rates.
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, 2,952 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.
