Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | spragsprag/symphonyRemove × | mistralaiVoxtral-Mini-3B-2507Remove × |
|---|---|---|
| What’s different | 19 languages | Voxtral Mini is an enhancement of Ministral 3B, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and… |
| Date | Oct 17, 2026Discovered | Jul 19, 2025Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | See provider quotes | $16.6667 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 0 endpoints → | 2 endpoints → |
Benchmarks Each result retains its evaluation configuration | ||
| AMI-Cleaned WER ↗English short-form; normalization unversioned | 9.02% WER ↗sprag/symphonyLeaderboard entry | 13.57% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | 6.01% WER ↗sprag/symphonyLeaderboard entry | 7.66% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | 7.52% WER ↗sprag/symphonyLeaderboard entry | 8.7% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | 1% WER ↗sprag/symphonyLeaderboard entry | 1.48% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | 2.19% WER ↗sprag/symphonyLeaderboard entry | 3.63% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | 2.21% WER ↗sprag/symphonyLeaderboard entry | 2.15% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | 12.64% WER ↗sprag/symphonyLeaderboard entry | 15.66% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | 3.55% WER ↗sprag/symphonyLeaderboard entry | 4.9% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | 3.33% WER ↗sprag/symphonyLeaderboard entry | 2.22% WER ↗mistralai/Voxtral-Mini-3B-2507Leaderboard entry |
Specifications | ||
| Context window | — | 32.8K |
| Max output | — | — |
| Parameters | — | 3B |
| Audio input | Supported | Supported |
| Transcription | Supported | Supported |
| Open weights | Not reported | Supported |