CekuraBench

Grok Voice 3.0vsGPT Realtime 2.1

All comparisonsLeaderboard
Compare
Grok Voice 3.0xAI
Wins 4 of 8
Reliability
81.7%
Response time
1.34s
Cost / min
$0.080
GPT Realtime 2.1OpenAI
Wins 3 of 8
Reliability
79.3%
Response time
1.94s
Cost / min
$0.085

Grok Voice 3.0 is ahead on reliability, calls where the agent went quiet, response time and cost, and GPT Realtime 2.1 on success rate, agent responses and data accuracy. The two tie on interruption.

Last updated Methodology by Dileep Chagam

Who is better at what

Grok Voice 3.0GPT Realtime 2.1
  • Reliability81.7%79.3%
  • Success rate86.6%89.0%
  • Agent responses97.2%99.2%
  • Data accuracy87.3%92.0%
  • Went quiet0.0%3.3%
  • Interruption4.984.98
  • Response time1.34s1.94s
  • Cost / min$0.080$0.085

Results by call

Right every time, on booking and Medicare calls

Booking callsMedicare calls
  1. 86%
    61%
    GPT Realtime 2.1
  2. 97%
    43%
    Grok Voice 3.0

Related comparisons

Both providers, every model: OpenAI vs xAI

Grok Voice 3.0 vs GPT Realtime 2.1 FAQ

  • Grok Voice 3.0 is more reliable, by 2.4 points. Grok Voice 3.0 passed 67 of 82 scenarios on all three runs, and GPT Realtime 2.1 passed 65. A scenario only counts when every run of it passed.

  • For a voice agent, Grok Voice 3.0, since it gets more scenarios right on every run. Grok Voice 3.0 is ahead on reliability, calls where the agent went quiet, response time and cost, and GPT Realtime 2.1 on success rate, agent responses and data accuracy. The two tie on interruption.

  • GPT Realtime 2.1, by 4.6 points. Grok Voice 3.0 saved everything exactly right on 87.3% of the calls that save data, and GPT Realtime 2.1 on 92.0%. On Booking calls, 98.2% against 95.9%. On Medicare calls, 59.1% against 81.8%. A call counts only when nothing is missing, wrong, extra or saved twice.

  • Yes. Grok Voice 3.0 starts replying 0.59s sooner at the median. Grok Voice 3.0 takes 1.34s at the median and 1.62s at p90; GPT Realtime 2.1 takes 1.94s and 2.46s. Both are measured on the call audio, from the caller finishing to the agent starting to reply.

  • They score the same. Grok Voice 3.0 scores 4.98 and GPT Realtime 2.1 4.98 for how well the agent handled being talked over.

  • Grok Voice 3.0, by 3.3 points. The agent went quiet for 10 seconds or more on 0.0% of Grok Voice 3.0 calls and 3.3% of GPT Realtime 2.1 calls.

  • Grok Voice 3.0 is $0.005 cheaper a minute. Grok Voice 3.0 costs $0.080 a minute of call and GPT Realtime 2.1 $0.085, 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, 3,198 calls across the benchmark. A call passes only when the agent said the right things and saved the right data.