GPT-Live 1 + GPT-6 Sol vs Higgs Realtime

GPT-Live 1 + GPT-6 Sol is more reliable, by 19.5 points. GPT-Live 1 + GPT-6 Sol passed 62 of 82 scenarios on all three runs, and Higgs Realtime passed 46. A scenario only counts when every run of it passed.

For a voice agent, GPT-Live 1 + GPT-6 Sol, since it gets more scenarios right on every run. GPT-Live 1 + GPT-6 Sol is ahead on reliability, success rate, agent responses and data accuracy, and Higgs Realtime on calls where the agent went quiet, interruption, response time and cost.

GPT-Live 1 + GPT-6 Sol, by 22.8 points. GPT-Live 1 + GPT-6 Sol saved everything exactly right on 89.0% of the calls that save data, and Higgs Realtime on 66.2%. On Booking calls, 100.0% against 91.8%. On Medicare calls, 60.6% against 0.0%. A call counts only when nothing is missing, wrong, extra or saved twice.

No. Higgs Realtime starts replying 0.08s sooner at the median. GPT-Live 1 + GPT-6 Sol takes 2.02s at the median and 2.42s at p90; Higgs Realtime takes 1.94s and 2.02s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

Higgs Realtime, by 0.11 on a 0 to 5 scale. GPT-Live 1 + GPT-6 Sol scores 4.89 and Higgs Realtime 5.00 for how well the agent handled being talked over.

Higgs Realtime, by 11.0 points. The agent went quiet for 10 seconds or more on 12.2% of GPT-Live 1 + GPT-6 Sol calls and 1.2% of Higgs Realtime calls.

Higgs Realtime is $0.0492 cheaper a minute. GPT-Live 1 + GPT-6 Sol costs $0.0553 a minute of call and Higgs Realtime $0.0061, 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, 3,690 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.