Gradium vs Murf Finch-Global

Compare

Accuracy and speed

Left gets fewer words wrong. Lower has the final text ready sooner.

Accurate and fast0ms200ms400ms600ms800ms0%2%4%6%Words wrong on clean audio (Pipecat WER)
  • Gradium4.02% · 219ms
  • Finch-Global3.17% · 51ms

Murf Finch-Global is ahead on both datasets together, the Pipecat Dataset and final-text delay, and Gradium on time to first text. The Ocular Dataset is too close to call.

Last updated Methodology by Dileep Chagam

Who is better at what

GradiumFinch-Global
  • Overall WER3.83%3.33%
  • Pipecat Dataset WER4.02%3.17%
  • Ocular Dataset WER3.47%3.62%
  • Time to first text1.78s1.83s
  • Final-text delay219ms51ms

Lower is better on every measure. Too close to call means the likely ranges overlap.

Clip by clip

On every clip both models were scored on, the lower WER wins, and WERs within 5 points of each other are a draw; in the rating, a wider win counts for more. Expected win rate is what the two ELO ratings predict for a match.

GradiumFinch-Global
  • ELO rating978973–983 · rank 15–21998981–1017 · rank 5–21
  • Expected win rate47%53%
  • Ocular turns WER · 170 draws of 19816 won12 won
  • Pipecat WER · 780 draws of 99988 won131 won
  • Semantic WER · 188 draws of 1987 won3 won
  • Phone line · 160 draws of 19822 won16 won
  • Call-center noise · 101 draws of 19815 won82 won
  • Babble noise · 97 draws of 19820 won81 won
  • TV noise · 150 draws of 19718 won29 won
  • Reverb · 136 draws of 19741 won20 won
  • Short replies · 60 draws of 706 won4 won
  • Entities · 41 draws of 506 won3 won

Short replies are decided on the error count and entities on exact capture, with no draw margin. How the rating is worked out

Gradium vs Finch-Global FAQ

  • Murf Finch-Global is more accurate on both datasets. On the 1,000 public Pipecat clips, Gradium scores 3.83% and Murf Finch-Global 3.33%, so Murf Finch-Global makes fewer errors by 0.51 points. On the 300 licensed Ocular turns, Gradium scores 4.02% and Murf Finch-Global 3.17%, so Murf Finch-Global makes fewer errors by 0.86 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Yes. Gradium finishes the transcript 57ms sooner. Gradium has the final transcript 1.78s after the speaker stops and Murf Finch-Global 1.83s, at the median. Both are measured on the same 206 streamed turns.

  • It is a trade-off. Murf Finch-Global makes fewer errors on real conversations, while Gradium finishes the transcript 57ms sooner. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.

  • Yes, both return partial text before the speaker stops. Gradium shows first text after 3.47% and Murf Finch-Global after 3.62%, at the median.

Test your voice agent the same way.

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