Benchmark run
Da recheck 1 6 827
Wispr Flow 1.6.872 external-product benchmark; da_dk clips 401-927 again on Flow 1.6.827
Sep 16, 2026
- Models
- 1
- Samples per dataset
- 527
- Warmup runs
- 3
- Hardware
- Apple M4 Max / 36 GB / macOS 26.6.2
Full results
Accuracy is the share of words transcribed correctly per language condition, so higher is better; speed is milliseconds per second of audio, so lower is better. The best value in each column is emphasised, and a cell reading a dash says on hover why there is no figure in it.
Accuracy (%) per language, and speed in ms per second of audio, so lower is better. A cell reading a dash was never measured, and hovering any cell says what is behind it.
| Wispr Flow | 527 | No disk file: it is a cloud product. | Memory of a cloud product cannot be observed. | 230 ms | 93.6%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 93.6%Every word from every language counted together, not an average of per-language scores. | 93.6% |
|---|
At a glance
Ratings computed from benchmark data, scaled 1 to 10, and written with their scale in every cell. Accuracy is based on Word Error Rate (WER) and does not include punctuation yet.
Ratings run 1 to 10, higher is better. A cell reading a dash was never measured, and hovering any cell says what is behind it.
| Wispr Flow | The languages this row covers were never recorded. | Whether this row translates was never recorded. | 4/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
|---|