Music Arena Vocal
Lyria 3 Pro 1,107 leads the models we track Models generate music with vocals. Listeners compare anonymous tracks, and separate vocal preference votes determine the Arena score.
Vocal votes form a separate pool from the instrumental leaderboard.
- Released
- July 2025
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Ranked by votes
- Answers
- Open-ended
- Tasks
- All public
- Last model added
- March 2026
- Scores refreshed
- November 12th, 2026
Riffusion FUZZ v1.0 tops the leaderboard with 1,132
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Lyria 3 Pro, at 1,107.
Bars start at 600.
- 1 Riffusion FUZZ v1.0 1,132
- 2 Lyria 3 Pro 1,107
- 3 Riffusion FUZZ v1.1 1,103
- 4 Sonauto v3 Preview 1,102
- 5 Lyria 3 Clip 1,019
- 6 ElevenLabs Music v1 998
- 7 Sonauto v2.2 944
- 8 ACE-Step 1.5 Turbo (1.7B) 939
- 9 ACE-Step 656
Source: Official Music Arena Vocal leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Riffusion FUZZ v1.0 | 1,132 | Official leaderboard | ||
| 2 | Lyria 3 Pro | 1,107 | Mar 2026 | Official leaderboard | |
| 3 | Riffusion FUZZ v1.1 | 1,103 | Official leaderboard | ||
| 4 | Sonauto v3 Preview | 1,102 | Official leaderboard | ||
| 5 | Lyria 3 Clip | 1,019 | Mar 2026 | Official leaderboard | |
| 6 | ElevenLabs Music v1 | 998 | Official leaderboard | ||
| 7 | Sonauto v2.2 | 944 | Official leaderboard | ||
| 8 | ACE-Step 1.5 Turbo (1.7B) | 939 | Official leaderboard | ||
| 9 | ACE-Step | 656 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Music Arena Vocal leaderboard
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy.
Qwen 3.8 Max 88.7% - LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
- MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
- FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better.
Phi-4-multimodal 4.00% - VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%