SunoAudio matchupMusic and sound
Suno v6vs.Suno v6-wild
Which model is better?
Suno v6 and Suno v6-wild perform about the same in independent tests.
Pick Suno v6 for
Pick Suno v6-wild for
Shared tests
Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.
YuE project, WildSongBench results
levelSuno v6 is clearly ahead in 0 of 6 subtests, Suno v6-wild in none. 6 are level.
WildSongBench SongEval musicality
192 tasks, as of October 17, 2026
WildSongBench SongEval average
192 tasks, as of October 17, 2026
WildSongBench MuLan text-audio similarity
192 tasks, as of October 17, 2026
Show all 6 subtests
| Subtest | Suno v6 | Suno v6-wild | Verdict |
|---|---|---|---|
| WildSongBench SongEval musicality | 4 | 4 | level |
| WildSongBench SongEval average | 4 | 4 | level |
| WildSongBench MuLan text-audio similarity | 0 | 0 | level |
| WildSongBench Q3O prompt control | 5 | 5 | level |
| WildSongBench AudioBox production quality | 8 | 8 | level |
| WildSongBench AllMusicCaps text-audio similarity | 0 | 0 | level |
Source · latest October 17, 2026
Vendor figures
Figures from vendor reports that cover both models. They do not count toward the verdict.
Show 3 vendor figures
| Figure | Source | Suno v6 | Suno v6-wild |
|---|---|---|---|
| Musicality | YuE2 model card | 5.66 | 5.56 |
| PER (lower is better) | YuE2 model card | 7.6 % | 7.5 % |
| SongBench average | YuE2 model card | 6.56 | 6.42 |
All data side by side
Prices are verbatim from the provider, because audio models bill per minute, character or token.
| Suno v6 | Suno v6-wild | |
|---|---|---|
| Task | Music and sound | Music and sound |
| Developer | Suno | Suno |
| Status | Active | Active |
| Released | September 9, 2026 | September 9, 2026 |
| Weights | proprietary | proprietary |
| Runs locally | no | no |
| Popularity (out of 100) | 0 | 0 |