Benchmark run
2026 09 v4 english tail
English clips 951 to corpus end, 13 multilingual models, matching the Flow depth
Sep 22, 2026
- Models
- 13
- Samples per dataset
- 1986
- 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.
| Whisper Large V3 Turbo Q8_0 | 1667 | 834 MB | 1.1 GB | 88 ms | 96.0%Every word from every language counted together, not an average of per-language scores. | 96.0%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 97.1% | 94.9% |
|---|---|---|---|---|---|---|---|---|---|
| Whisper Large V3 Turbo Q5_0 | 1667 | 574 MB | 783 MB | 80 ms | 95.9%Every word from every language counted together, not an average of per-language scores. | 95.9%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 97.1% | 94.9% |
| Whisper Large V3 Q5_0 | 1667 | 1.1 GB | 1.6 GB | 123 ms | 95.9%Every word from every language counted together, not an average of per-language scores. | 95.9%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 97.1% | 94.8% |
| Whisper Large V3 | 1667 | 3.0 GB | 3.5 GB | 192 ms | 95.9%Every word from every language counted together, not an average of per-language scores. | 95.9%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 97.1% | 94.8% |
| Whisper Large V3 Turbo | 1667 | 1.6 GB | 1.9 GB | 111 ms | 95.9%Every word from every language counted together, not an average of per-language scores. | 95.9%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 97.1% | 94.7% |
| Whisper Large V2 | 1667 | 3.0 GB | 3.5 GB | 193 ms | 95.4%Every word from every language counted together, not an average of per-language scores. | 95.4%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 96.8% | 94.1% |
| Whisper Large V2 Q8_0 | 1667 | 1.6 GB | 2.1 GB | 142 ms | 95.4%Every word from every language counted together, not an average of per-language scores. | 95.4%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 96.8% | 94.1% |
| Whisper Large V2 Q5_0 | 1667 | 1.1 GB | 1.5 GB | 124 ms | 95.4%Every word from every language counted together, not an average of per-language scores. | 95.4%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 96.8% | 94.0% |
| Whisper Large V1 | 1667 | 3.0 GB | 3.5 GB | 194 ms | 95.2%Every word from every language counted together, not an average of per-language scores. | 95.2%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 96.7% | 93.7% |
| Parakeet TDT 0.6B v3 | 1667 | 500 MB | 79 MB | 9 ms | 95.2%Every word from every language counted together, not an average of per-language scores. | 95.2%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 96.2% | 94.2% |
| Whisper Medium | 1667 | 1.5 GB | 1.9 GB | 108 ms | 94.8%Every word from every language counted together, not an average of per-language scores. | 94.8%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 96.4% | 93.4% |
| Whisper Medium Q8_0 | 1667 | 766 MB | 1.2 GB | 82 ms | 94.8%Every word from every language counted together, not an average of per-language scores. | 94.8%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 96.4% | 93.4% |
| Whisper Medium Q5_0 | 1667 | 514 MB | 881 MB | 74 ms | 94.8%Every word from every language counted together, not an average of per-language scores. | 94.8%Every word from every language counted together, not an average of per-language scores. | Not scored on any benchmark language. | 96.4% | 93.3% |
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.
| Whisper Large V3 Turbo Q5_0 | All languages | No | 8/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
|---|---|---|---|---|
| Whisper Large V3 Q5_0 | All languages | Yes | 7/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Parakeet TDT 0.6B v3 | 25 languages | No | 10/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Whisper Large V1 | All languages | Yes | 5/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Whisper Large V2 | All languages | Yes | 5/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Whisper Large V2 Q5_0 | All languages | Yes | 7/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Whisper Large V2 Q8_0 | All languages | Yes | 6/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Whisper Large V3 | All languages | Yes | 5/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Whisper Large V3 Turbo | All languages | No | 7/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Whisper Large V3 Turbo Q8_0 | All languages | No | 8/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Whisper Medium | All languages | Yes | 7/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Whisper Medium Q5_0 | All languages | Yes | 8/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
| Whisper Medium Q8_0 | All languages | Yes | 8/10 | 10/10Every word from every language counted together, not an average of per-language scores. |
Charts
The plots generated alongside this run. Select a chart to open it full size.
