Realtime ranker
Every realtime model. Same audio. Scored on responsiveness, stability, and accuracy — the axes that matter when words appear as you speak.
1
Models Ranked
1
Total Benchmarks
11
Languages Tested
Jul 14, 2026
Last Updated
01
Flux
27.2
290 ms TTFP
3050.0% flicker
0 ms drain
98.41% WER
weighted composite
50%
Accuracy
WER vs. reference transcripts, streamed live
25%
Responsiveness
Median time to first partial transcript
20%
Stability
How often earlier partials get revised before finalizing
5%
Tail latency
Final-chunk drain time after audio stops
how responsiveness is measured
TTFP
Time to First Partial
How quickly the model starts showing words (lower is better)
Flicker
Flicker
How often earlier partial words change before the transcript finalizes (lower is better)
Cadence
Cadence
How often the model updates its partial transcript — descriptive context, not scored
RTF
Real-Time Factor
Reads ≈1.0 for a well-behaved realtime model since audio is streamed at real-time pace — not a 'lower is always better' metric like batch speed factor
One endpoint, every provider. Pin the leader or let us auto-route to the best model under your accuracy and latency budget.